A Survey on Multi-Task Learning

Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks. In this paper, we give a survey for MTL from the perspective of algorithmic modeling...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on knowledge and data engineering Ročník 34; číslo 12; s. 5586 - 5609
Hlavní autoři:	Zhang, Yu, Yang, Qiang
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.12.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithms artificial intelligence Classification algorithms Clustering Cognitive tasks Computational modeling Data models Machine learning Modelling Multi-task learning Performance enhancement Supervised learning Task analysis Training Transfer learning
ISSN:	1041-4347, 1558-2191
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks. In this paper, we give a survey for MTL from the perspective of algorithmic modeling, applications and theoretical analyses. For algorithmic modeling, we give a definition of MTL and then classify different MTL algorithms into five categories, including feature learning approach, low-rank approach, task clustering approach, task relation learning approach and decomposition approach as well as discussing the characteristics of each approach. In order to improve the performance of learning tasks further, MTL can be combined with other learning paradigms including semi-supervised learning, active learning, unsupervised learning, reinforcement learning, multi-view learning and graphical models. When the number of tasks is large or the data dimensionality is high, we review online, parallel and distributed MTL models as well as dimensionality reduction and feature hashing to reveal their computational and storage advantages. Many real-world applications use MTL to boost their performance and we review representative works in this paper. Finally, we present theoretical analyses and discuss several future directions for MTL.
AbstractList	Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks. In this paper, we give a survey for MTL from the perspective of algorithmic modeling, applications and theoretical analyses. For algorithmic modeling, we give a definition of MTL and then classify different MTL algorithms into five categories, including feature learning approach, low-rank approach, task clustering approach, task relation learning approach and decomposition approach as well as discussing the characteristics of each approach. In order to improve the performance of learning tasks further, MTL can be combined with other learning paradigms including semi-supervised learning, active learning, unsupervised learning, reinforcement learning, multi-view learning and graphical models. When the number of tasks is large or the data dimensionality is high, we review online, parallel and distributed MTL models as well as dimensionality reduction and feature hashing to reveal their computational and storage advantages. Many real-world applications use MTL to boost their performance and we review representative works in this paper. Finally, we present theoretical analyses and discuss several future directions for MTL.
Author	Zhang, Yu Yang, Qiang
Author_xml	– sequence: 1 givenname: Yu orcidid: 0000-0003-1100-4835 surname: Zhang fullname: Zhang, Yu email: yu.zhang.ust@gmail.com organization: Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China – sequence: 2 givenname: Qiang surname: Yang fullname: Yang, Qiang email: qyang@cse.ust.hk organization: Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong
BookMark	eNp9kDtPwzAUhS1UJNrCD0AMRGJOuX4ktseqlIcoYqDMluPcoJTiFDup1H9PqlYMDEz3Duc7R_pGZOAbj4RcUphQCvp2-Xw3nzBgdMJBAgN-QoY0y1TKqKaD_gdBU8GFPCOjGFcAoKSiQ3I9Td66sMVd0vjkpVu3dbq08TNZoA2-9h_n5LSy64gXxzsm7_fz5ewxXbw-PM2mi9QxzdvU6SpXWKJyutTggGe8zIpcSV0468pCACIFWuVaFM4JWWiKGorMomYVZ5aPyc2hdxOa7w5ja1ZNF3w_aZjkgqssV6pP0UPKhSbGgJXZhPrLhp2hYPYezN6D2XswRw89I_8wrm5tWze-DbZe_0teHcgaEX-XNNeM5zn_AU29arQ
CODEN	ITKEEH
CitedBy_id	crossref_primary_10_1016_j_iswa_2025_200567 crossref_primary_10_1145_3665252_3665263 crossref_primary_10_1145_3664615 crossref_primary_10_3390_info15070381 crossref_primary_10_20965_jaciii_2024_p0029 crossref_primary_10_1016_j_eswa_2025_126966 crossref_primary_10_1016_j_jbi_2025_104872 crossref_primary_10_1109_TMI_2024_3362852 crossref_primary_10_1016_j_compbiomed_2024_108549 crossref_primary_10_1016_j_asoc_2025_113823 crossref_primary_10_1109_TASLP_2024_3353578 crossref_primary_10_1109_TGRS_2024_3506058 crossref_primary_10_1002_lpor_202200698 crossref_primary_10_1038_s43588_024_00662_z crossref_primary_10_1142_S0219519425400743 crossref_primary_10_1177_10692509251337224 crossref_primary_10_3390_su16177259 crossref_primary_10_1109_JBHI_2023_3291433 crossref_primary_10_3390_app15179602 crossref_primary_10_1109_LRA_2025_3588784 crossref_primary_10_1016_j_jbi_2025_104881 crossref_primary_10_1016_j_asoc_2025_113834 crossref_primary_10_1016_j_comcom_2023_03_028 crossref_primary_10_1109_TGRS_2021_3099300 crossref_primary_10_1016_j_cmpb_2025_108918 crossref_primary_10_1109_ACCESS_2024_3376441 crossref_primary_10_1007_s10489_024_06023_7 crossref_primary_10_1016_j_eswa_2025_126972 crossref_primary_10_1016_j_eswa_2025_126987 crossref_primary_10_1109_TIM_2023_3250306 crossref_primary_10_1007_s10489_021_02930_1 crossref_primary_10_1109_TNNLS_2023_3306896 crossref_primary_10_3390_electronics12071631 crossref_primary_10_1007_s10115_025_02517_z crossref_primary_10_1109_TPAMI_2023_3346386 crossref_primary_10_1088_2632_2153_ac37f7 crossref_primary_10_3390_s22103637 crossref_primary_10_3390_en18071783 crossref_primary_10_1007_s00521_023_08263_z crossref_primary_10_1093_jamia_ocae061 crossref_primary_10_1109_TIM_2024_3449957 crossref_primary_10_1109_TCYB_2020_3036935 crossref_primary_10_1109_TKDE_2023_3305628 crossref_primary_10_1093_bib_bbae539 crossref_primary_10_1016_j_knosys_2024_112386 crossref_primary_10_1016_j_compmedimag_2025_102539 crossref_primary_10_1109_JSEN_2024_3352260 crossref_primary_10_1109_TVT_2023_3260466 crossref_primary_10_1109_TIV_2023_3256972 crossref_primary_10_1016_j_isprsjprs_2025_06_022 crossref_primary_10_1093_bib_bbad203 crossref_primary_10_1109_TGRS_2024_3487652 crossref_primary_10_1109_ACCESS_2024_3443148 crossref_primary_10_1002_mma_11217 crossref_primary_10_1109_JIOT_2025_3579524 crossref_primary_10_1016_j_ins_2025_122154 crossref_primary_10_2139_ssrn_5347645 crossref_primary_10_1109_TVCG_2024_3456142 crossref_primary_10_1016_j_bspc_2025_108395 crossref_primary_10_1109_ACCESS_2023_3303110 crossref_primary_10_1109_TNNLS_2022_3183081 crossref_primary_10_1016_j_autcon_2023_105184 crossref_primary_10_3390_e25040696 crossref_primary_10_1088_1361_6501_ad6892 crossref_primary_10_1109_LRA_2025_3564781 crossref_primary_10_1049_ipr2_70098 crossref_primary_10_3390_s25185620 crossref_primary_10_1002_we_2909 crossref_primary_10_3390_diagnostics15091177 crossref_primary_10_1007_s10845_025_02630_4 crossref_primary_10_1016_j_eswa_2023_122845 crossref_primary_10_1145_3664650 crossref_primary_10_1016_j_atmosenv_2023_120193 crossref_primary_10_1016_j_eswa_2025_128940 crossref_primary_10_3390_s23031083 crossref_primary_10_1002_rnc_8057 crossref_primary_10_3390_rs14143450 crossref_primary_10_1109_TPEL_2025_3565730 crossref_primary_10_3389_fpsyg_2021_652796 crossref_primary_10_1002_cjs_70022 crossref_primary_10_3390_s25010224 crossref_primary_10_3390_su151410816 crossref_primary_10_1017_asb_2025_10 crossref_primary_10_1145_3563947 crossref_primary_10_1002_bit_28757 crossref_primary_10_3390_rs15163934 crossref_primary_10_1109_TCOMM_2023_3238373 crossref_primary_10_1007_s00521_025_11603_w crossref_primary_10_3389_fped_2023_1144952 crossref_primary_10_3390_jcm12237355 crossref_primary_10_1080_13658816_2024_2381146 crossref_primary_10_1145_3569480 crossref_primary_10_3390_s25134095 crossref_primary_10_1038_s41598_025_01893_4 crossref_primary_10_1145_3640468 crossref_primary_10_1109_TCBB_2022_3220902 crossref_primary_10_1109_TWC_2022_3231088 crossref_primary_10_1007_s10664_024_10466_4 crossref_primary_10_1007_s10845_024_02348_9 crossref_primary_10_1186_s12859_022_05031_z crossref_primary_10_1109_JIOT_2022_3228292 crossref_primary_10_1109_TGRS_2024_3511618 crossref_primary_10_3390_en18061531 crossref_primary_10_1109_JIOT_2024_3505553 crossref_primary_10_1109_TG_2024_3436871 crossref_primary_10_1109_ACCESS_2024_3490772 crossref_primary_10_3390_app15010057 crossref_primary_10_1007_s10489_024_05828_w crossref_primary_10_1007_s42243_025_01530_4 crossref_primary_10_1186_s12911_024_02814_7 crossref_primary_10_3934_mina_2025004 crossref_primary_10_1109_TCSVT_2024_3451294 crossref_primary_10_1016_j_knosys_2024_112187 crossref_primary_10_1109_TIM_2023_3273673 crossref_primary_10_1016_j_isprsjprs_2023_10_022 crossref_primary_10_32604_cmes_2024_048071 crossref_primary_10_1002_sres_3139 crossref_primary_10_1109_JIOT_2025_3559731 crossref_primary_10_3390_math12040534 crossref_primary_10_1109_TMI_2023_3287361 crossref_primary_10_1016_j_eswa_2025_128971 crossref_primary_10_1007_s13042_023_01877_8 crossref_primary_10_1287_ijds_2024_0029 crossref_primary_10_1109_TASLPRO_2025_3539018 crossref_primary_10_1007_s11227_024_06422_0 crossref_primary_10_3390_app15158733 crossref_primary_10_1145_3639816 crossref_primary_10_1016_j_energy_2024_133960 crossref_primary_10_1109_TIM_2024_3379372 crossref_primary_10_1080_03461238_2025_2478439 crossref_primary_10_1155_atr_9961530 crossref_primary_10_1007_s10462_024_10929_6 crossref_primary_10_3390_s24247975 crossref_primary_10_1080_00207543_2023_2275635 crossref_primary_10_1016_j_neucom_2024_129076 crossref_primary_10_1109_TKDE_2020_2999489 crossref_primary_10_1109_ACCESS_2025_3601992 crossref_primary_10_1109_TPAMI_2023_3283780 crossref_primary_10_1109_TSIPN_2024_3352236 crossref_primary_10_1109_TCSVT_2024_3514740 crossref_primary_10_3390_rs17142442 crossref_primary_10_1109_TIM_2023_3276529 crossref_primary_10_3390_electronics14153009 crossref_primary_10_1007_s11263_024_02089_5 crossref_primary_10_1016_j_compbiomed_2025_110050 crossref_primary_10_4000_ijcol_553 crossref_primary_10_3389_fpls_2023_1048016 crossref_primary_10_3390_app112411808 crossref_primary_10_1016_j_jfca_2025_108160 crossref_primary_10_1016_j_ymssp_2024_112299 crossref_primary_10_1016_j_jmapro_2024_08_036 crossref_primary_10_1109_TCSS_2024_3443275 crossref_primary_10_1016_j_patcog_2024_110599 crossref_primary_10_1038_s41565_025_01975_4 crossref_primary_10_3390_s24165343 crossref_primary_10_1016_j_commatsci_2024_112897 crossref_primary_10_1016_j_procs_2025_05_039 crossref_primary_10_1016_j_engappai_2023_107714 crossref_primary_10_1111_bph_16140 crossref_primary_10_1016_j_modpat_2024_100691 crossref_primary_10_1093_nsr_nwaf231 crossref_primary_10_1016_j_eswa_2025_126583 crossref_primary_10_3390_ijms26062510 crossref_primary_10_1145_3511896 crossref_primary_10_1016_j_patcog_2024_111213 crossref_primary_10_1109_TASE_2024_3375300 crossref_primary_10_1016_j_autcon_2024_105292 crossref_primary_10_3390_app15158740 crossref_primary_10_1016_j_bspc_2025_107678 crossref_primary_10_1371_journal_pone_0258639 crossref_primary_10_1007_s10115_024_02168_6 crossref_primary_10_1109_ACCESS_2024_3509918 crossref_primary_10_1109_TASE_2025_3551593 crossref_primary_10_1117_1_JEI_33_1_013048 crossref_primary_10_3390_rs16071193 crossref_primary_10_1016_j_optlaseng_2023_107923 crossref_primary_10_3390_app13116802 crossref_primary_10_1145_3656170 crossref_primary_10_1145_3678181 crossref_primary_10_3390_math13050824 crossref_primary_10_1016_j_jbi_2023_104434 crossref_primary_10_3390_rs15061487 crossref_primary_10_1016_j_mtcomm_2025_113054 crossref_primary_10_1016_j_camwa_2025_01_007 crossref_primary_10_1109_TKDE_2022_3149815 crossref_primary_10_1016_j_vehcom_2024_100760 crossref_primary_10_1038_s42256_025_01109_4 crossref_primary_10_3389_fnins_2025_1557287 crossref_primary_10_1007_s00607_025_01499_8 crossref_primary_10_1007_s11042_024_20413_6 crossref_primary_10_3390_math11224639 crossref_primary_10_1109_TBME_2022_3175670 crossref_primary_10_1109_TED_2023_3327973 crossref_primary_10_1016_j_neunet_2024_107031 crossref_primary_10_1016_j_scitotenv_2024_173273 crossref_primary_10_1038_s43247_025_02502_y crossref_primary_10_1016_j_solener_2025_113336 crossref_primary_10_1109_ACCESS_2024_3480358 crossref_primary_10_1111_exsy_70127 crossref_primary_10_1109_JSEN_2024_3454646 crossref_primary_10_1007_s00521_023_08461_9 crossref_primary_10_3390_s24175552 crossref_primary_10_1007_s10207_025_00992_7 crossref_primary_10_1007_s11263_024_02304_3 crossref_primary_10_1109_TNNLS_2024_3416191 crossref_primary_10_1016_j_compbiomed_2025_110003 crossref_primary_10_3390_ijgi14050189 crossref_primary_10_1016_j_patcog_2024_110794 crossref_primary_10_1109_ACCESS_2023_3294979 crossref_primary_10_1007_s10589_023_00475_2 crossref_primary_10_3390_electronics14071262 crossref_primary_10_1145_3731596 crossref_primary_10_3390_molecules26226959 crossref_primary_10_1016_j_knosys_2025_114047 crossref_primary_10_1109_TDSC_2023_3247869 crossref_primary_10_3390_s23249729 crossref_primary_10_1016_j_compstruct_2023_117555 crossref_primary_10_1002_jcc_70157 crossref_primary_10_1109_TGRS_2023_3344103 crossref_primary_10_1016_j_swevo_2025_101931 crossref_primary_10_1109_ACCESS_2024_3471613 crossref_primary_10_1109_JLT_2024_3401244 crossref_primary_10_1093_nsr_nwx105 crossref_primary_10_1016_j_cviu_2024_104138 crossref_primary_10_1109_TAFE_2024_3485949 crossref_primary_10_1109_TPAMI_2024_3357847 crossref_primary_10_1109_TNNLS_2022_3225179 crossref_primary_10_1109_TGRS_2024_3356008 crossref_primary_10_1109_TMC_2024_3357874 crossref_primary_10_1109_TNNLS_2024_3475216 crossref_primary_10_1080_02626667_2025_2561163 crossref_primary_10_1016_j_colsurfa_2024_134133 crossref_primary_10_1088_2057_1976_ada6bd crossref_primary_10_1109_ACCESS_2022_3151670 crossref_primary_10_1016_j_ins_2025_122112 crossref_primary_10_3389_frobt_2023_1283322 crossref_primary_10_3390_f14091697 crossref_primary_10_1016_j_compeleceng_2025_110640 crossref_primary_10_1109_TSUSC_2024_3350040 crossref_primary_10_1016_j_engstruct_2024_118171 crossref_primary_10_1109_TII_2024_3413352 crossref_primary_10_1016_j_neunet_2025_107315 crossref_primary_10_1177_18758967251353020 crossref_primary_10_1016_j_eswa_2025_127002 crossref_primary_10_3390_s24113282 crossref_primary_10_3390_make5030062 crossref_primary_10_1109_TMM_2022_3187257 crossref_primary_10_3348_jksr_2022_0155 crossref_primary_10_3390_aerospace9100603 crossref_primary_10_1109_TVT_2024_3454208 crossref_primary_10_1109_TMC_2025_3547339 crossref_primary_10_1016_j_vetpar_2025_110525 crossref_primary_10_1049_cit2_12197 crossref_primary_10_1080_10618600_2023_2252023 crossref_primary_10_1109_TBME_2024_3365131 crossref_primary_10_1109_TMC_2023_3344125 crossref_primary_10_1109_TVT_2024_3511697 crossref_primary_10_1177_00368504241292196 crossref_primary_10_3390_w16152156 crossref_primary_10_3390_rs16203891 crossref_primary_10_1016_j_patcog_2024_110424 crossref_primary_10_1016_j_asoc_2025_113044 crossref_primary_10_1016_j_neucom_2024_127736 crossref_primary_10_1177_03611981231155418 crossref_primary_10_1287_mnsc_2023_00309 crossref_primary_10_1109_TIE_2024_3379664 crossref_primary_10_1016_j_trc_2025_105146 crossref_primary_10_1007_s00521_024_10767_1 crossref_primary_10_1145_3543870 crossref_primary_10_1016_j_jmapro_2023_08_030 crossref_primary_10_1109_TIV_2024_3426970 crossref_primary_10_3390_app15010409 crossref_primary_10_1213_ANE_0000000000007278 crossref_primary_10_1109_TGRS_2021_3136159 crossref_primary_10_1007_s10489_024_05548_1 crossref_primary_10_1016_j_neunet_2024_106513 crossref_primary_10_1016_j_measurement_2025_118770 crossref_primary_10_1088_1361_6501_ad0a21 crossref_primary_10_1109_ACCESS_2024_3510746 crossref_primary_10_1016_j_compbiomed_2022_106496 crossref_primary_10_1016_j_iot_2024_101406 crossref_primary_10_3389_fpubh_2021_793801 crossref_primary_10_1016_j_jenvman_2023_118817 crossref_primary_10_1109_TAI_2021_3104789 crossref_primary_10_1016_j_knosys_2024_112701 crossref_primary_10_1109_TNNLS_2022_3169347 crossref_primary_10_1016_j_optlastec_2024_110655 crossref_primary_10_1038_s41591_025_03916_z crossref_primary_10_1016_j_patcog_2023_109592 crossref_primary_10_1109_ACCESS_2025_3578009 crossref_primary_10_1038_s41598_024_52463_z crossref_primary_10_1016_j_neunet_2024_106528 crossref_primary_10_1007_s10589_024_00607_2 crossref_primary_10_1002_aisy_202300270 crossref_primary_10_1088_1402_4896_ada20a crossref_primary_10_1088_1741_4326_ade16d crossref_primary_10_1145_3722103 crossref_primary_10_1016_j_jbi_2024_104711 crossref_primary_10_1145_3725854 crossref_primary_10_1109_ACCESS_2024_3518483 crossref_primary_10_1145_3656479 crossref_primary_10_1109_TSP_2021_3122303 crossref_primary_10_1109_TASLP_2022_3214763 crossref_primary_10_3390_rs16183522 crossref_primary_10_1016_j_tre_2024_103900 crossref_primary_10_1016_j_neucom_2024_127533 crossref_primary_10_1111_risa_70066 crossref_primary_10_1088_1741_2552_ad731b crossref_primary_10_1016_j_knosys_2024_111672 crossref_primary_10_1109_TIV_2023_3319546 crossref_primary_10_1109_JBHI_2021_3119519 crossref_primary_10_26599_BDMA_2024_9020049 crossref_primary_10_1145_3571072 crossref_primary_10_1016_j_autcon_2025_106306 crossref_primary_10_1016_j_neucom_2025_131586 crossref_primary_10_1109_TBME_2024_3523044 crossref_primary_10_1016_j_conengprac_2025_106579 crossref_primary_10_1109_TII_2024_3441652 crossref_primary_10_1016_j_csl_2023_101606 crossref_primary_10_32604_cmc_2023_046711 crossref_primary_10_1016_j_aei_2024_102565 crossref_primary_10_1109_JBHI_2024_3454097 crossref_primary_10_3390_app15042216 crossref_primary_10_1109_ACCESS_2024_3383442 crossref_primary_10_1016_j_neucom_2025_130008 crossref_primary_10_1109_TAFFC_2025_3555406 crossref_primary_10_1109_TMC_2025_3568470 crossref_primary_10_1109_TMI_2022_3156614 crossref_primary_10_1007_s00034_025_03127_4 crossref_primary_10_1016_j_eswa_2024_125978 crossref_primary_10_1016_j_neucom_2025_131333 crossref_primary_10_1109_TPAMI_2023_3292075 crossref_primary_10_1109_TIM_2022_3173636 crossref_primary_10_1007_s11768_023_00165_8 crossref_primary_10_3390_electronics13112115 crossref_primary_10_1016_j_knosys_2025_113911 crossref_primary_10_3389_fpls_2024_1340884 crossref_primary_10_1016_j_ese_2025_100592 crossref_primary_10_1016_j_ins_2024_120147 crossref_primary_10_3390_rs16020215 crossref_primary_10_1007_s10010_025_00875_2 crossref_primary_10_1016_j_jss_2025_112629 crossref_primary_10_1016_j_knosys_2023_111133 crossref_primary_10_1016_j_jvcir_2025_104484 crossref_primary_10_1016_j_inffus_2025_103657 crossref_primary_10_3390_s23239536 crossref_primary_10_1109_OJCOMS_2025_3534626 crossref_primary_10_3390_rs17152688 crossref_primary_10_1007_s10462_024_10855_7 crossref_primary_10_1016_j_ijfatigue_2023_107864 crossref_primary_10_1145_3501807 crossref_primary_10_1007_s10287_022_00425_z crossref_primary_10_1088_1741_2552_ad9956 crossref_primary_10_1109_JBHI_2022_3181791 crossref_primary_10_1088_1757_899X_1261_1_012018 crossref_primary_10_1016_j_omega_2024_103073 crossref_primary_10_1109_TPAMI_2020_3015859 crossref_primary_10_1109_TKDE_2024_3366333 crossref_primary_10_3390_rs14215624 crossref_primary_10_1007_s10462_024_10846_8 crossref_primary_10_1145_3663363 crossref_primary_10_1109_TMC_2024_3466227 crossref_primary_10_1109_TAI_2024_3400750 crossref_primary_10_3390_app142210540 crossref_primary_10_1016_j_ijforecast_2025_01_005 crossref_primary_10_1016_j_ymssp_2024_111418 crossref_primary_10_3390_s23218894 crossref_primary_10_7554_eLife_65554 crossref_primary_10_1287_ijds_2023_0022 crossref_primary_10_3389_fneur_2025_1640428 crossref_primary_10_1109_TCCN_2025_3558992 crossref_primary_10_3390_electronics13142835 crossref_primary_10_1109_TCYB_2024_3422430 crossref_primary_10_1109_TCSVT_2025_3544680 crossref_primary_10_1016_j_engappai_2023_107189 crossref_primary_10_1016_j_neucom_2025_130217 crossref_primary_10_1109_TAFFC_2022_3170428 crossref_primary_10_1016_j_aeue_2025_155915 crossref_primary_10_1109_TNSE_2021_3056655 crossref_primary_10_1109_TAFFC_2022_3205170 crossref_primary_10_1016_j_ins_2023_119015 crossref_primary_10_69709_COConnect_2024_097213 crossref_primary_10_1007_s00521_024_10436_3 crossref_primary_10_1177_19462174251330980 crossref_primary_10_1287_ijds_2023_0029 crossref_primary_10_1109_ACCESS_2025_3574982 crossref_primary_10_1016_j_knosys_2024_112570 crossref_primary_10_1109_TII_2022_3170594 crossref_primary_10_3390_s25134115 crossref_primary_10_1016_j_nlp_2023_100048 crossref_primary_10_1016_j_compbiomed_2023_107450 crossref_primary_10_1007_s11222_024_10550_1 crossref_primary_10_3390_s22218452 crossref_primary_10_1016_j_rse_2023_113924 crossref_primary_10_1109_JSTARS_2025_3567472 crossref_primary_10_1038_s41467_025_56062_y crossref_primary_10_1016_j_compind_2024_104131 crossref_primary_10_1016_j_lwt_2024_116436 crossref_primary_10_1016_j_knosys_2025_113704 crossref_primary_10_1007_s11370_023_00489_z crossref_primary_10_1109_TASLPRO_2025_3590289 crossref_primary_10_1109_TMM_2022_3164798 crossref_primary_10_1111_cgf_14795 crossref_primary_10_1109_COMST_2024_3503680 crossref_primary_10_1007_s13042_023_01795_9 crossref_primary_10_1109_TIFS_2025_3592544 crossref_primary_10_1177_02783649241227448 crossref_primary_10_1016_j_ast_2025_110241 crossref_primary_10_1016_j_ast_2025_110483 crossref_primary_10_1109_TPAMI_2022_3218605 crossref_primary_10_1016_j_compbiomed_2025_110846 crossref_primary_10_3390_math11183821 crossref_primary_10_1021_acs_analchem_5c03263 crossref_primary_10_1109_TVT_2023_3344127 crossref_primary_10_1109_ACCESS_2024_3449072 crossref_primary_10_1016_j_measurement_2025_118139 crossref_primary_10_1016_j_cherd_2023_05_016 crossref_primary_10_1145_3749458 crossref_primary_10_1109_TKDE_2024_3392836 crossref_primary_10_1177_14759217231206178 crossref_primary_10_1109_ACCESS_2023_3312993 crossref_primary_10_1109_TGRS_2025_3528333 crossref_primary_10_1109_TASLP_2022_3221042 crossref_primary_10_1111_tgis_70092 crossref_primary_10_1109_TIM_2025_3575181 crossref_primary_10_3389_fpsyg_2025_1575174 crossref_primary_10_1145_3609483 crossref_primary_10_1145_3530990 crossref_primary_10_1109_ACCESS_2024_3512544 crossref_primary_10_1109_TAI_2024_3477457 crossref_primary_10_1016_j_eneco_2025_108226 crossref_primary_10_3390_agronomy15040793 crossref_primary_10_1109_TII_2022_3190394 crossref_primary_10_3390_s24020681 crossref_primary_10_1109_JSEN_2025_3588616 crossref_primary_10_1109_TVCG_2023_3282802 crossref_primary_10_1016_j_ins_2024_120564 crossref_primary_10_1109_ACCESS_2025_3568002 crossref_primary_10_1109_TWC_2025_3543176 crossref_primary_10_1016_j_compstruc_2025_107840 crossref_primary_10_1088_2632_2153_ac4f3f crossref_primary_10_1109_JSEN_2025_3563154 crossref_primary_10_3390_app13116784 crossref_primary_10_1016_j_cie_2024_110763 crossref_primary_10_1109_TCSS_2024_3475511 crossref_primary_10_1109_THMS_2022_3176213 crossref_primary_10_1088_1361_6579_ac9d7f crossref_primary_10_1109_TCSVT_2024_3375344 crossref_primary_10_1145_3514252 crossref_primary_10_1109_TMI_2023_3323540 crossref_primary_10_1371_journal_pone_0302958 crossref_primary_10_1109_TAFFC_2022_3210958 crossref_primary_10_1109_TMI_2022_3218720 crossref_primary_10_1016_j_array_2025_100444 crossref_primary_10_1038_s41467_024_53101_y crossref_primary_10_1016_j_jmsy_2024_04_021 crossref_primary_10_1038_s41598_023_45466_9 crossref_primary_10_1016_j_inffus_2023_102135 crossref_primary_10_1109_TETCI_2024_3359082 crossref_primary_10_1016_j_neucom_2025_130638 crossref_primary_10_1109_TITS_2020_3019390 crossref_primary_10_1016_j_neucom_2025_129898 crossref_primary_10_1109_TASLP_2021_3060813 crossref_primary_10_1016_j_engappai_2023_106276 crossref_primary_10_1109_ACCESS_2022_3181750 crossref_primary_10_1016_j_rse_2023_113962 crossref_primary_10_2196_60003 crossref_primary_10_1007_s41060_024_00574_1 crossref_primary_10_1109_TPAMI_2021_3054719 crossref_primary_10_1016_j_mineng_2024_109148 crossref_primary_10_1016_j_neucom_2024_129105 crossref_primary_10_1038_s42256_024_00966_9 crossref_primary_10_1002_aisy_202400204 crossref_primary_10_1016_j_neucom_2025_130865 crossref_primary_10_1016_j_aei_2024_103052 crossref_primary_10_1109_JSEN_2025_3541212 crossref_primary_10_1007_s10844_023_00787_z crossref_primary_10_1016_j_aej_2025_03_115 crossref_primary_10_1088_1361_6501_adeacf crossref_primary_10_1109_TNNLS_2023_3280085 crossref_primary_10_1007_s41060_024_00697_5 crossref_primary_10_1016_j_neucom_2024_128260 crossref_primary_10_1109_TMC_2022_3207164 crossref_primary_10_1007_s10115_025_02460_z crossref_primary_10_1109_TGRS_2025_3550867 crossref_primary_10_1109_TVCG_2022_3167896 crossref_primary_10_1016_j_eswa_2025_126855 crossref_primary_10_1109_TCOMM_2024_3381671 crossref_primary_10_1007_s11263_025_02502_7 crossref_primary_10_1016_j_engstruct_2024_118079 crossref_primary_10_1109_ACCESS_2025_3588506 crossref_primary_10_1007_s10462_024_10817_z crossref_primary_10_1016_j_inffus_2023_101891 crossref_primary_10_3390_machines13060475 crossref_primary_10_1016_j_cmpb_2023_107399 crossref_primary_10_1007_s11227_025_07643_7 crossref_primary_10_1038_s41598_025_10650_6 crossref_primary_10_1007_s10489_025_06270_2 crossref_primary_10_1016_j_ijmedinf_2024_105567 crossref_primary_10_1016_j_asoc_2024_112568 crossref_primary_10_3390_electronics13142689 crossref_primary_10_1016_j_compmedimag_2025_102646 crossref_primary_10_1190_geo2024_0348_1 crossref_primary_10_5406_21521123_62_2_03 crossref_primary_10_1117_1_OE_63_11_111812 crossref_primary_10_1002_mp_17266 crossref_primary_10_1016_j_compchemeng_2025_109253 crossref_primary_10_1080_20539320_2022_2150470 crossref_primary_10_1007_s00170_022_10115_4 crossref_primary_10_3390_math11173751 crossref_primary_10_1109_ACCESS_2022_3175311 crossref_primary_10_1016_j_eswa_2023_119975 crossref_primary_10_1007_s10114_025_3362_8 crossref_primary_10_1038_s41598_025_85859_6 crossref_primary_10_1016_j_bspc_2023_105615 crossref_primary_10_1016_j_neucom_2024_129136 crossref_primary_10_1016_j_bspc_2024_107081 crossref_primary_10_1038_s40494_025_01949_8 crossref_primary_10_1080_01621459_2021_1987251 crossref_primary_10_1109_LSP_2023_3336570 crossref_primary_10_1109_TNNLS_2023_3330879 crossref_primary_10_1109_TITS_2023_3309600 crossref_primary_10_1016_j_future_2025_107798 crossref_primary_10_1109_TCSS_2024_3442238 crossref_primary_10_1016_j_artint_2024_104184 crossref_primary_10_1109_ACCESS_2025_3566719 crossref_primary_10_1109_TGRS_2024_3497338 crossref_primary_10_1007_s10796_023_10372_y crossref_primary_10_1016_j_physleta_2025_130516 crossref_primary_10_1016_j_engappai_2024_107936 crossref_primary_10_1016_j_eswa_2024_124189 crossref_primary_10_1145_3665868 crossref_primary_10_1109_JSTSP_2023_3267263 crossref_primary_10_1016_j_ins_2025_122060 crossref_primary_10_1038_s41598_025_98111_y crossref_primary_10_3390_s24237463 crossref_primary_10_1109_ACCESS_2022_3147495 crossref_primary_10_1088_1361_6560_acb481 crossref_primary_10_3390_math10234525 crossref_primary_10_1007_s10489_024_05805_3 crossref_primary_10_2118_223950_PA crossref_primary_10_3390_jcp5020029 crossref_primary_10_3390_jpm13030413 crossref_primary_10_1016_j_cmpb_2025_108830 crossref_primary_10_1109_JBHI_2025_3536030 crossref_primary_10_1016_j_apsb_2025_09_022 crossref_primary_10_1109_TKDE_2021_3124599 crossref_primary_10_1016_j_cmpb_2025_108835 crossref_primary_10_1109_TAFFC_2025_3537799 crossref_primary_10_1016_j_neucom_2024_129163 crossref_primary_10_1016_j_psep_2023_10_015 crossref_primary_10_1007_s40747_023_01221_1 crossref_primary_10_1177_03611981211016852 crossref_primary_10_3390_rs15194752 crossref_primary_10_1109_TIFS_2022_3186803 crossref_primary_10_1016_j_bspc_2023_105665 crossref_primary_10_1007_s11042_023_14333_0 crossref_primary_10_1145_3728467 crossref_primary_10_1007_s11042_024_20175_1 crossref_primary_10_1111_mice_13224 crossref_primary_10_1109_LRA_2024_3502061 crossref_primary_10_1109_JIOT_2024_3371978 crossref_primary_10_1051_wujns_2024292134 crossref_primary_10_1093_bib_bbad523 crossref_primary_10_1016_j_media_2025_103480 crossref_primary_10_1007_s11633_024_1523_3 crossref_primary_10_1109_TCE_2024_3357480 crossref_primary_10_1109_ACCESS_2024_3434513 crossref_primary_10_1109_TEMC_2024_3472031 crossref_primary_10_1109_TETCI_2024_3485704 crossref_primary_10_1016_j_drudis_2025_104366 crossref_primary_10_1016_j_swevo_2025_102084 crossref_primary_10_1109_JIOT_2023_3317639 crossref_primary_10_1287_isre_2022_0358 crossref_primary_10_1109_TII_2024_3366946 crossref_primary_10_1177_09544070251364016 crossref_primary_10_3390_math12111733 crossref_primary_10_3390_app142310821 crossref_primary_10_1097_TA_0000000000004624 crossref_primary_10_1109_COMST_2024_3443193 crossref_primary_10_1016_j_est_2025_116002 crossref_primary_10_1145_3639930 crossref_primary_10_1016_j_cja_2025_103757 crossref_primary_10_1016_j_egyai_2025_100585 crossref_primary_10_1016_j_rse_2023_113580 crossref_primary_10_1109_TKDE_2024_3372462 crossref_primary_10_1080_1206212X_2025_2520496 crossref_primary_10_1016_j_knosys_2025_114109 crossref_primary_10_1109_JAS_2023_123618 crossref_primary_10_1016_j_engappai_2025_110107 crossref_primary_10_1109_JPROC_2023_3273517 crossref_primary_10_1109_TPAMI_2021_3057446 crossref_primary_10_1007_s11227_025_07297_5 crossref_primary_10_1016_j_aei_2025_103185 crossref_primary_10_1109_ACCESS_2025_3564115 crossref_primary_10_1016_j_jfranklin_2023_04_024 crossref_primary_10_1007_s11704_022_1437_6 crossref_primary_10_1016_j_knosys_2025_113249 crossref_primary_10_1109_JBHI_2022_3204776 crossref_primary_10_1016_j_optlaseng_2024_108177 crossref_primary_10_1016_j_eswa_2023_122773 crossref_primary_10_1109_ACCESS_2024_3525000 crossref_primary_10_1016_j_neuroimage_2024_120695 crossref_primary_10_1016_j_eng_2025_08_008 crossref_primary_10_1029_2022GL102283 crossref_primary_10_1007_s11257_022_09332_z crossref_primary_10_1016_j_ins_2023_119908 crossref_primary_10_1109_TAFFC_2024_3404243 crossref_primary_10_1016_j_energy_2024_132976 crossref_primary_10_1109_TEVC_2021_3139437 crossref_primary_10_1016_j_engappai_2025_110122 crossref_primary_10_1109_TMM_2022_3147664 crossref_primary_10_3390_s23249806 crossref_primary_10_1007_s00376_024_3222_y crossref_primary_10_1016_j_inffus_2023_03_015 crossref_primary_10_1016_j_psep_2023_11_046 crossref_primary_10_1109_TCCN_2023_3328986 crossref_primary_10_1001_jamanetworkopen_2023_36196 crossref_primary_10_1109_LRA_2024_3440093 crossref_primary_10_1109_TETC_2024_3390811 crossref_primary_10_1109_TGRS_2021_3075622 crossref_primary_10_3389_fnins_2023_1158280 crossref_primary_10_1016_j_eswa_2024_126187 crossref_primary_10_1016_j_neunet_2024_106234 crossref_primary_10_1038_s41698_024_00700_z crossref_primary_10_1109_TAFFC_2023_3282410 crossref_primary_10_1002_lary_30516 crossref_primary_10_1103_PhysRevLett_134_177301 crossref_primary_10_1016_j_jisa_2023_103555 crossref_primary_10_1002_aisy_202300318 crossref_primary_10_1016_j_dsp_2025_105168 crossref_primary_10_1002_wics_70021 crossref_primary_10_1061_JMENEA_MEENG_6699 crossref_primary_10_1109_ACCESS_2023_3258975 crossref_primary_10_1109_JSEN_2024_3390231 crossref_primary_10_1080_0305215X_2024_2434201 crossref_primary_10_1007_s10489_023_04917_6 crossref_primary_10_1007_s00371_023_02962_3 crossref_primary_10_1109_JSYST_2023_3263865 crossref_primary_10_1109_TPWRS_2022_3155865 crossref_primary_10_1002_aisy_202400922 crossref_primary_10_1088_1741_4326_ade3ed crossref_primary_10_1109_TGRS_2025_3543270 crossref_primary_10_1287_ijoc_2023_0366 crossref_primary_10_1109_LSP_2022_3159402 crossref_primary_10_1016_j_neunet_2024_106292 crossref_primary_10_1016_j_apenergy_2025_125851 crossref_primary_10_1109_LCOMM_2021_3136508 crossref_primary_10_1109_ACCESS_2024_3404990 crossref_primary_10_1111_exsy_70017 crossref_primary_10_1007_s41019_025_00303_z crossref_primary_10_1109_TITS_2024_3411638 crossref_primary_10_1016_j_knosys_2025_114384 crossref_primary_10_1109_TGRS_2022_3169703 crossref_primary_10_1109_LWC_2022_3163810 crossref_primary_10_1016_j_joi_2024_101607 crossref_primary_10_1109_TIM_2022_3225056 crossref_primary_10_1038_s41598_023_29230_7 crossref_primary_10_3390_su16062475 crossref_primary_10_1109_TIM_2025_3548240 crossref_primary_10_3390_rs13163083 crossref_primary_10_1016_j_applthermaleng_2025_128005 crossref_primary_10_1088_1742_5468_adf296 crossref_primary_10_1007_s00202_024_02327_6 crossref_primary_10_1109_TBME_2024_3402677 crossref_primary_10_1016_j_cja_2024_10_019 crossref_primary_10_1016_j_renene_2025_123011 crossref_primary_10_1049_enc2_12125 crossref_primary_10_1109_TMM_2024_3390148 crossref_primary_10_1109_TKDE_2024_3351732 crossref_primary_10_1109_TSE_2023_3292399 crossref_primary_10_1007_s10579_025_09827_2 crossref_primary_10_1088_1361_6501_adc473 crossref_primary_10_3233_SW_222991 crossref_primary_10_1109_MCI_2022_3222049 crossref_primary_10_1109_TSP_2025_3588910 crossref_primary_10_1007_s11042_025_21046_z crossref_primary_10_1038_s41598_025_97262_2 crossref_primary_10_1016_j_bspc_2025_108441 crossref_primary_10_1109_TPAMI_2025_3588685 crossref_primary_10_1016_j_compind_2023_103978 crossref_primary_10_1109_TMI_2022_3223405 crossref_primary_10_3389_fnins_2025_1606038 crossref_primary_10_3390_smartcities7050095 crossref_primary_10_1007_s44336_024_00004_7 crossref_primary_10_1109_TAES_2023_3253085 crossref_primary_10_1371_journal_pone_0327663 crossref_primary_10_1007_s41066_021_00285_z crossref_primary_10_1016_j_atmosenv_2024_120775 crossref_primary_10_1109_TKDE_2024_3419449 crossref_primary_10_1016_j_rse_2025_114964 crossref_primary_10_1109_TKDE_2024_3385712 crossref_primary_10_1016_j_bspc_2023_105081 crossref_primary_10_1016_j_inffus_2024_102358 crossref_primary_10_1109_ACCESS_2025_3556587 crossref_primary_10_3390_jimaging8110293 crossref_primary_10_1002_aisy_202401093 crossref_primary_10_1109_TMM_2022_3233245 crossref_primary_10_1109_TIM_2023_3267520 crossref_primary_10_1016_j_neucom_2024_128701 crossref_primary_10_1109_TMC_2025_3559676 crossref_primary_10_4018_JOEUC_379722 crossref_primary_10_1016_j_jad_2025_01_136 crossref_primary_10_1016_j_knosys_2023_111236 crossref_primary_10_1109_ACCESS_2025_3534798 crossref_primary_10_1016_j_eswa_2025_129671 crossref_primary_10_1016_j_aquaculture_2025_743001 crossref_primary_10_1016_j_eswa_2025_128584 crossref_primary_10_1038_s41524_025_01554_0 crossref_primary_10_1145_3723349 crossref_primary_10_1109_LSENS_2023_3266430 crossref_primary_10_1109_TCYB_2020_3017736 crossref_primary_10_1109_TGRS_2023_3328339 crossref_primary_10_1109_TVCG_2023_3337868 crossref_primary_10_1016_j_ecoinf_2024_102784 crossref_primary_10_1016_j_slast_2025_100283 crossref_primary_10_1007_s13042_025_02794_8 crossref_primary_10_1109_TMI_2022_3222730 crossref_primary_10_1007_s10596_023_10255_w crossref_primary_10_1016_j_engappai_2024_109593 crossref_primary_10_3390_ai4030039 crossref_primary_10_1109_TNSM_2023_3236348 crossref_primary_10_1287_isre_2023_0591 crossref_primary_10_1109_JIOT_2023_3299262 crossref_primary_10_1109_TBDATA_2025_3556612 crossref_primary_10_1016_j_neucom_2025_131251 crossref_primary_10_1021_acssensors_4c03209 crossref_primary_10_1016_j_jag_2025_104397 crossref_primary_10_1016_j_patcog_2025_111922 crossref_primary_10_1038_s41598_025_92769_0 crossref_primary_10_1177_20552076251343696 crossref_primary_10_1016_j_engappai_2024_109144 crossref_primary_10_3390_en15134602 crossref_primary_10_1088_2632_2153_ad4e04 crossref_primary_10_1007_s10845_025_02658_6 crossref_primary_10_1049_cvi2_12289 crossref_primary_10_1038_s41467_025_59822_y crossref_primary_10_1088_1475_7516_2025_03_072 crossref_primary_10_1016_j_dsp_2025_105209 crossref_primary_10_1016_j_jbi_2023_104545 crossref_primary_10_1007_s11432_023_3823_6 crossref_primary_10_1038_s41597_024_03878_w crossref_primary_10_1016_j_dsp_2025_105444 crossref_primary_10_3390_math12172634 crossref_primary_10_1007_s11192_024_04996_3 crossref_primary_10_1109_TGRS_2023_3283217 crossref_primary_10_1016_j_jpi_2023_100357 crossref_primary_10_1190_geo2021_0342_1 crossref_primary_10_1109_TNSM_2023_3281133 crossref_primary_10_1016_j_actaastro_2024_08_045 crossref_primary_10_1109_TITS_2023_3336358 crossref_primary_10_1016_j_neucom_2023_02_018 crossref_primary_10_1109_ACCESS_2022_3172958 crossref_primary_10_1007_s00521_022_06914_1 crossref_primary_10_1016_j_compbiomed_2025_109798 crossref_primary_10_1016_j_eswa_2024_123419 crossref_primary_10_1109_JBHI_2021_3085526 crossref_primary_10_1016_j_molliq_2025_128568 crossref_primary_10_1016_j_jseaes_2024_106369 crossref_primary_10_1109_TUFFC_2022_3190012 crossref_primary_10_1109_JIOT_2023_3320149 crossref_primary_10_1109_TCBB_2021_3102584 crossref_primary_10_1109_JRFID_2024_3371881 crossref_primary_10_1088_1361_6501_adba7e crossref_primary_10_1109_TKDE_2024_3378482 crossref_primary_10_3390_app13148433 crossref_primary_10_1109_RBME_2023_3296938 crossref_primary_10_1016_j_exer_2025_110394 crossref_primary_10_3390_s25175387 crossref_primary_10_1016_j_segan_2025_101766 crossref_primary_10_1016_j_compeleceng_2024_110045 crossref_primary_10_1016_j_robot_2023_104580 crossref_primary_10_1007_s00521_025_11148_y crossref_primary_10_3390_electronics12132986 crossref_primary_10_1109_ACCESS_2022_3144406 crossref_primary_10_1109_TITS_2025_3560182 crossref_primary_10_1109_TGRS_2025_3531493 crossref_primary_10_1016_j_fuel_2023_129343 crossref_primary_10_1109_TII_2022_3191980 crossref_primary_10_1109_TEVC_2023_3272663 crossref_primary_10_1109_ACCESS_2024_3485616 crossref_primary_10_1109_TGRS_2022_3176670 crossref_primary_10_1007_s10664_024_10526_9 crossref_primary_10_3390_app11115303 crossref_primary_10_1016_j_nlp_2025_100133 crossref_primary_10_1021_acs_iecr_5c01161 crossref_primary_10_1007_s11517_025_03391_1 crossref_primary_10_1016_j_jmsy_2025_08_005 crossref_primary_10_1109_ACCESS_2025_3556327 crossref_primary_10_4018_JOEUC_374213 crossref_primary_10_1007_s00521_024_10165_7 crossref_primary_10_1016_j_ocemod_2025_102550 crossref_primary_10_1111_jiec_70048 crossref_primary_10_1007_s12145_025_01905_x crossref_primary_10_1016_j_measurement_2025_117526 crossref_primary_10_1109_TNSM_2022_3224803 crossref_primary_10_23919_AISE_2025_000008 crossref_primary_10_3390_app13137761 crossref_primary_10_1007_s00500_024_09886_7 crossref_primary_10_3390_biomedicines10010070 crossref_primary_10_1007_s00500_025_10646_4 crossref_primary_10_1109_TAI_2025_3530383 crossref_primary_10_1016_j_actamat_2025_121161 crossref_primary_10_1109_ACCESS_2024_3360004 crossref_primary_10_1155_2023_5639207 crossref_primary_10_1016_j_geoen_2024_213608 crossref_primary_10_1109_JPROC_2024_3435012 crossref_primary_10_1007_s13042_023_01892_9 crossref_primary_10_1016_j_neunet_2023_11_043 crossref_primary_10_3390_app14073073 crossref_primary_10_1109_TGRS_2025_3563661 crossref_primary_10_1109_TASE_2024_3516378 crossref_primary_10_1109_TKDE_2022_3203904 crossref_primary_10_1109_JSEN_2021_3132943 crossref_primary_10_1121_10_0011809 crossref_primary_10_1007_s10115_025_02366_w crossref_primary_10_1186_s12880_023_01109_z crossref_primary_10_1109_ACCESS_2025_3580056 crossref_primary_10_1145_3663476 crossref_primary_10_3390_computers13120343 crossref_primary_10_1109_ACCESS_2024_3497011 crossref_primary_10_1007_s40747_025_01816_w crossref_primary_10_1109_TSP_2025_3546458 crossref_primary_10_1007_s10999_025_09773_5 crossref_primary_10_1109_TCOMM_2022_3225920 crossref_primary_10_1016_j_bspc_2024_106857 crossref_primary_10_1145_3747181 crossref_primary_10_1016_j_inffus_2023_102217 crossref_primary_10_1016_j_ress_2025_111209 crossref_primary_10_1016_j_ins_2024_121705 crossref_primary_10_1007_s00521_022_07717_0 crossref_primary_10_1007_s11063_023_11396_w crossref_primary_10_1109_TNNLS_2023_3281473 crossref_primary_10_4018_IJITSA_345397 crossref_primary_10_1190_geo2024_0260_1 crossref_primary_10_1109_JSTARS_2021_3139017 crossref_primary_10_1088_1741_2552_ad17f4 crossref_primary_10_1590_1981_5344_58057 crossref_primary_10_1109_TIFS_2025_3580224 crossref_primary_10_1016_j_neucom_2025_130792 crossref_primary_10_1109_TSP_2023_3322791 crossref_primary_10_1109_TGRS_2024_3354783 crossref_primary_10_1186_s12911_024_02510_6 crossref_primary_10_1016_j_compbiomed_2025_110718 crossref_primary_10_1109_JIOT_2025_3535744 crossref_primary_10_1186_s12859_023_05524_5 crossref_primary_10_1016_j_neucom_2025_130307 crossref_primary_10_1016_j_isprsjprs_2023_09_001 crossref_primary_10_1007_s00521_025_11451_8 crossref_primary_10_1155_2021_1834428 crossref_primary_10_1109_TKDE_2020_3006048 crossref_primary_10_1109_TIV_2024_3405561 crossref_primary_10_1016_j_neucom_2024_127255 crossref_primary_10_3390_fi17070287 crossref_primary_10_1016_j_rser_2023_114094 crossref_primary_10_1007_s00521_023_09374_3 crossref_primary_10_1093_bib_bbaf408 crossref_primary_10_1109_TNSRE_2024_3395133 crossref_primary_10_1016_j_patcog_2025_112347 crossref_primary_10_1109_TIM_2022_3189735 crossref_primary_10_1109_TIM_2025_3568524 crossref_primary_10_1109_TGRS_2025_3540573 crossref_primary_10_1109_ACCESS_2023_3309050 crossref_primary_10_1016_j_knosys_2025_112995 crossref_primary_10_1038_s41467_025_56481_x crossref_primary_10_1016_j_eswa_2024_124570 crossref_primary_10_1016_j_knosys_2024_112254 crossref_primary_10_1016_j_patcog_2025_111491 crossref_primary_10_1109_TGRS_2022_3208226 crossref_primary_10_1016_j_sciaf_2023_e01799 crossref_primary_10_3390_app12136296 crossref_primary_10_1109_TAES_2023_3293074 crossref_primary_10_3390_signals4010009 crossref_primary_10_1145_3625820 crossref_primary_10_1109_JBHI_2025_3545927 crossref_primary_10_1109_ACCESS_2023_3322457 crossref_primary_10_1109_LRA_2023_3271445 crossref_primary_10_3390_biomimetics9110708 crossref_primary_10_1007_s00521_023_08335_0 crossref_primary_10_1016_j_ymssp_2023_111051 crossref_primary_10_1167_iovs_65_2_5 crossref_primary_10_1016_j_apenergy_2025_126255 crossref_primary_10_1007_s10115_025_02379_5 crossref_primary_10_1109_JIOT_2023_3281329 crossref_primary_10_4081_jae_2024_1606 crossref_primary_10_1016_j_neucom_2022_09_042 crossref_primary_10_1109_ACCESS_2024_3509033
Cites_doi	10.1109/TPAMI.2014.2343221 10.1609/aaai.v33i01.33013796 10.1137/1.9781611974010.56 10.1109/ICCV.2013.86 10.1145/1553374.1553458 10.18653/v1/P17-1001 10.1145/2499907.2499910 10.1007/11776420_34 10.1145/1835804.1835953 10.1109/CVPR.2014.186 10.1093/nsr/nwx105 10.1186/1471-2105-11-S8-S5 10.1109/TPAMI.2016.2537337 10.1007/978-3-319-10599-4_7 10.1561/2400000003 10.1145/2339530.2339672 10.1109/ICCV.2011.6126528 10.1109/CVPR.2015.7298994 10.1109/TCBB.2010.22 10.1145/2783258.2783393 10.1214/09-AOS776 10.1017/9781139061773 10.1007/s11263-014-0767-8 10.1145/2939672.2939834 10.1109/TKDE.2017.2657624 10.24963/ijcai.2017/253 10.1145/2020408.2020423 10.1145/1390156.1390253 10.1145/2339530.2339617 10.1137/1.9781611974010.57 10.1609/aaai.v29i1.9558 10.1109/TITS.2016.2598356 10.1609/aaai.v25i1.7914 10.1145/2623330.2623641 10.1109/CVPR.2013.61 10.1109/CVPR.2010.5539967 10.1609/aaai.v30i1.10261 10.1109/TKDE.2017.2662006 10.1109/ICCV.2015.383 10.1145/2747879 10.1109/TCYB.2014.2344015 10.1109/TBDATA.2016.2573280 10.1109/CVPR.2015.7298608 10.1109/TPAMI.2008.296 10.1145/3097983.3098152 10.1109/ICDM.2015.68 10.21437/Interspeech.2016-879 10.1145/1273496.1273624 10.1145/1553374.1553392 10.1007/978-3-642-04174-7_40 10.1186/1471-2105-11-181 10.24963/ijcai.2018/435 10.1109/TPAMI.2008.297 10.1007/s10994-007-5040-8 10.1145/1143844.1143900 10.1109/ICASSP.2015.7178780 10.24963/ijcai.2019/505 10.1089/cmb.2016.0201 10.1613/jair.731 10.1137/090763184 10.1109/TIP.2011.2169274 10.21437/Interspeech.2015-659 10.1109/TNNLS.2016.2521602 10.1007/978-0-387-85774-9_8 10.1109/ICDM.2016.0035 10.1145/1390156.1390177 10.1007/978-1-4419-9011-2 10.1109/TKDE.2016.2603983 10.1609/aaai.v29i1.9581 10.1093/bioinformatics/btq191 10.1007/978-3-319-24486-0_13 10.1109/ICASSP.2011.5946926 10.1016/j.neunet.2019.01.012 10.1007/s10994-008-5088-0 10.1609/aaai.v33i01.33015636 10.1109/TCYB.2015.2403356 10.1109/TKDE.2013.39 10.1007/s10994-017-5676-y 10.1093/bioinformatics/btq394 10.1109/TMM.2015.2477680 10.1109/ICDM.2015.130 10.1609/aaai.v28i1.9009 10.1109/TKDE.2017.2703106 10.1109/CVPR.2010.5539975 10.1609/aaai.v24i1.7674 10.1609/aaai.v31i1.10820 10.1137/1.9781611973440.22 10.1145/225298.225336 10.1145/1553374.1553516 10.1093/bioinformatics/btt245 10.1007/11776420_8 10.1145/2538028 10.1007/978-3-642-12683-3_34 10.1109/ICCV.2015.430 10.1145/3097983.3098136 10.1145/1102351.1102479 10.1093/bioinformatics/btq181 10.1093/bioinformatics/btw249 10.1609/aaai.v27i1.8577 10.1109/CVPR.2016.433 10.1609/aaai.v27i1.8557 10.1145/2783258.2783377 10.1007/s10994-013-5379-y 10.1007/978-3-642-33460-3_50 10.1109/TPAMI.2015.2452911 10.1109/ICCV.2013.150 10.1145/2396761.2398508 10.1162/NECO_a_00844 10.21437/Interspeech.2015-265 10.1145/1014052.1014067 10.1145/1273496.1273583 10.1093/bioinformatics/bty457 10.1145/1835804.1835952 10.1145/1645953.1646169 10.1007/s10994-007-5043-5 10.1109/TSP.2008.924798 10.1145/1390156.1390159 10.1109/ICASSP.2015.7178814 10.1145/2939672.2939857 10.1145/2020408.2020549 10.1609/aaai.v25i1.7909 10.1137/1.9781611975673.2 10.1109/TPAMI.2017.2679002 10.1145/1390156.1390164 10.1145/1273496.1273630 10.1023/A:1007379606734 10.1145/2556195.2556264 10.1007/s11263-012-0582-z 10.1137/1.9781611974348.74 10.1186/1471-2105-12-389
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TKDE.2021.3070203
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library Online url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	1558-2191
EndPage	5609
ExternalDocumentID	10_1109_TKDE_2021_3070203 9392366
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China; NSFC grantid: 62076118 funderid: 10.13039/501100001809
GroupedDBID	-~X .DC 0R~ 29I 4.4 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 UHB AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c293t-c9f68ede8c9d90c0353d5b6879bcacdb40ee101f694bcc47b91e90b5ae92f32a3
IEDL.DBID	RIE
ISICitedReferencesCount	1355
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000880645200003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1041-4347
IngestDate	Sun Nov 09 05:29:55 EST 2025 Sat Nov 29 02:36:03 EST 2025 Tue Nov 18 22:28:57 EST 2025 Wed Aug 27 02:18:57 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	12
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c293t-c9f68ede8c9d90c0353d5b6879bcacdb40ee101f694bcc47b91e90b5ae92f32a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-1100-4835
PQID	2734385688
PQPubID	85438
PageCount	24
ParticipantIDs	crossref_primary_10_1109_TKDE_2021_3070203 ieee_primary_9392366 crossref_citationtrail_10_1109_TKDE_2021_3070203 proquest_journals_2734385688
PublicationCentury	2000
PublicationDate	2022-12-01
PublicationDateYYYYMMDD	2022-12-01
PublicationDate_xml	– month: 12 year: 2022 text: 2022-12-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on knowledge and data engineering
PublicationTitleAbbrev	TKDE
PublicationYear	2022
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref57 ref56 ref59 ref205 ref58 ref206 ref204 ref55 ref201 ref202 zhang (ref79) 2010 wan (ref217) 2012 ref209 zhang (ref167) 2015 ref211 ref51 ref218 ref45 ref219 ref216 ref41 ref215 ref44 ref212 ref213 görnitz (ref75) 2011 gong (ref106) 2012 rusu (ref152) 2016 ref7 ref9 ref4 wang (ref223) 2012 ref3 jacob (ref61) 2008 ref5 ref100 ref221 agarwal (ref42) 2010 ref101 ref222 kumar (ref66) 2012 ref220 yim (ref208) 2015 solnon (ref107) 2012; 13 sener (ref115) 2018 kakade (ref255) 2012; 13 bonilla (ref76) 2007 ref34 ref33 guo (ref164) 2020 zweig (ref103) 2013 honorio (ref172) 2010 lozano (ref31) 2012 wang (ref32) 2014 ref20 omidshafiei (ref153) 2017 zhang (ref108) 2018 ref22 wang (ref210) 2009 ref21 yang (ref47) 2017 wang (ref186) 2016 ref27 saha (ref181) 2011 ref29 chai (ref77) 2009 li (ref128) 2009 oyen (ref173) 2012 ref200 lounici (ref263) 2009 parameswaran (ref70) 2010 thrun (ref48) 1996 kolar (ref265) 2011; 12 deshmukh (ref146) 2017 ref249 ref129 yu (ref116) 2020 ref126 ref247 ref127 li (ref142) 2009; 10 kim (ref35) 2010 ref99 ref124 ref245 ref246 crammer (ref49) 2012 bakker (ref50) 2003; 4 pentina (ref130) 2017 ref133 ref254 ref134 ref131 ref252 ref132 ref253 ref250 sharma (ref157) 2018 ref139 tutunov (ref159) 2018 ref258 ref85 ref138 ref135 ref87 ref257 wimalawarne (ref114) 2014 bsat (ref155) 2017 rai (ref92) 2012 hernández-lobato (ref38) 2013 ref82 passos (ref60) 2012 ref81 zhang (ref233) 2010 ref264 ref140 yang (ref6) 2009 ref141 ref80 ref229 ref109 ref227 ref228 ref104 sharma (ref156) 2017 ref74 ref226 ref224 yang (ref90) 2013 wang (ref214) 2011 ref232 chai (ref234) 2008 ref111 ref230 xue (ref54) 2007; 8 ref231 ref119 ref238 ref69 ref239 ref118 ref236 ref63 ref237 ref65 ref235 reichart (ref125) 2008 kato (ref72) 2007 rao (ref26) 2013 chen (ref117) 2018 argyriou (ref11) 2007 ref243 ref244 ref123 lugosi (ref178) 2009 ref241 ref120 ref242 ref121 ref240 zhang (ref96) 2013 alamgir (ref225) 2010 zhu (ref13) 2011 zhong (ref102) 2012 zhang (ref137) 2016 bräm (ref148) 2019 ref168 ref169 cavallanti (ref179) 2010; 11 ref170 dekel (ref177) 2007; 8 ref175 ref176 ref174 hernández-lobato (ref39) 2015 lazaric (ref143) 2010 zhang (ref91) 2013 wang (ref136) 2015 zhou (ref36) 2010 lee (ref97) 2016 dinuzzo (ref83) 2011 zhang (ref248) 2017 ref180 rakitsch (ref93) 2013 ref188 calandriello (ref144) 2014 ref187 ref184 titsias (ref14) 2011 ref185 evgeniou (ref71) 2005; 6 ref183 lee (ref25) 2010 ref149 parisotto (ref151) 2016 obozinski (ref23) 2006 yousefi (ref260) 2018; 19 smith (ref189) 2017 zhang (ref43) 2005 barzilai (ref64) 2015 liu (ref122) 2007 zhang (ref192) 2012 zhang (ref37) 2010 maurer (ref12) 2013 d’eramo (ref161) 2020 long (ref95) 2017 romera-paredes (ref113) 2013 maurer (ref259) 2016; 17 zhang (ref88) 2010 teh (ref154) 2017 ref166 ref163 liao (ref8) 2005 quadrianto (ref112) 2010 ref15 he (ref165) 2011 ref10 lian (ref53) 2015 ciliberto (ref84) 2015 ref17 ref16 ref19 luong (ref207) 2016 gong (ref30) 2013; 14 zheng (ref203) 2008 yu (ref52) 2007 zhang (ref78) 2010 archambeau (ref89) 2011 pontil (ref256) 2013 argyriou (ref261) 2009; 10 lin (ref160) 2019 mcdonald (ref46) 2014 zhou (ref68) 2011 wang (ref28) 2015 han (ref110) 2012 liu (ref24) 2009 maurer (ref251) 2006; 7 kang (ref62) 2011 andreas (ref145) 2017 murugesan (ref182) 2016 espeholt (ref158) 2018 jalali (ref98) 2010 ref2 ref1 ref191 gonçalves (ref94) 2016; 7 ref190 ando (ref40) 2005; 6 ref199 ref197 ref195 feldman (ref73) 2014; 15 ref196 ref193 ref194 argyriou (ref262) 2010; 11 mrksic (ref18) 2015 igl (ref150) 2020 jawanpuria (ref86) 2015 yang (ref67) 2017 ghosn (ref198) 1996 shu (ref162) 2018 jawanpuria (ref105) 2012 niculescu-mizil (ref171) 2012 saxe (ref147) 2017
References_xml	– ident: ref135 doi: 10.1109/TPAMI.2014.2343221 – start-page: 2411 year: 2014 ident: ref32 article-title: On multiplicative multitask feature learning publication-title: Proc Int Conf Neural Inf Process – start-page: 279 year: 2009 ident: ref77 article-title: Generalization errors and learning curves for regression with multi-task Gaussian processes publication-title: Proc 22nd Int Conf Neural Inf Process Syst – ident: ref163 doi: 10.1609/aaai.v33i01.33013796 – start-page: 2202 year: 2013 ident: ref26 article-title: Sparse overlapping sets lasso for multitask learning and its application to fMRI analysis publication-title: Proc Int Conf Neural Inf Process – ident: ref227 doi: 10.1137/1.9781611974010.56 – ident: ref244 doi: 10.1109/ICCV.2013.86 – start-page: 134 year: 2019 ident: ref148 article-title: Attentive multi-task deep reinforcement learning publication-title: Proc Eur Conf Mach Learn Knowl Discovery Databases – start-page: 339 year: 2009 ident: ref24 article-title: Multi-task feature learning via efficient $l_{2,1}$l2,1-norm minimization publication-title: Proc 25th Conf Uncertainty Artif Intell – volume: 14 start-page: 2979 year: 2013 ident: ref30 article-title: Multi-stage multi-task feature learning publication-title: J Mach Learn Res – ident: ref29 doi: 10.1145/1553374.1553458 – ident: ref21 doi: 10.18653/v1/P17-1001 – start-page: 969 year: 2020 ident: ref150 article-title: Multitask soft option learning publication-title: Proc Conf Uncertainty Artif Intell – ident: ref82 doi: 10.1145/2499907.2499910 – ident: ref176 doi: 10.1007/11776420_34 – start-page: 2339 year: 2011 ident: ref14 article-title: Spike and slab variational inference for multi-task and multiple kernel learning publication-title: Proc 24th Int Conf Neural Inf Process Syst – ident: ref231 doi: 10.1145/1835804.1835953 – ident: ref205 doi: 10.1109/CVPR.2014.186 – start-page: 595 year: 2012 ident: ref31 article-title: Multi-level lasso for sparse multi-task regression publication-title: Proc 29th Int Conf Mach Learn – year: 2016 ident: ref152 article-title: Policy distillation publication-title: Proc Int Conf Learn Representations – ident: ref5 doi: 10.1093/nsr/nwx105 – start-page: 861 year: 2008 ident: ref125 article-title: Multi-task active learning for linguistic annotations publication-title: Proc Annual Meeting of the Assoc Computational Linguistics – ident: ref236 doi: 10.1186/1471-2105-11-S8-S5 – start-page: 265 year: 2008 ident: ref234 article-title: Multi-task Gaussian process learning of robot inverse dynamics publication-title: Proc Int Conf Neural Inf Process – start-page: 4055 year: 2015 ident: ref167 article-title: Multi-task multi-view clustering for non-negative data publication-title: Proc Int Joint Conf Artif Intell – ident: ref229 doi: 10.1109/TPAMI.2016.2537337 – start-page: 1620 year: 2011 ident: ref13 article-title: Infinite latent SVM for classification and multi-task learning publication-title: Proc 24th Int Conf Neural Inf Process Syst – ident: ref15 doi: 10.1007/978-3-319-10599-4_7 – ident: ref118 doi: 10.1561/2400000003 – ident: ref101 doi: 10.1145/2339530.2339672 – ident: ref220 doi: 10.1109/ICCV.2011.6126528 – start-page: 2042 year: 2012 ident: ref192 article-title: Robust visual tracking via multi-task sparse learning publication-title: Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit – ident: ref16 doi: 10.1109/CVPR.2015.7298994 – ident: ref194 doi: 10.1109/TCBB.2010.22 – ident: ref104 doi: 10.1145/2783258.2783393 – start-page: 363 year: 2012 ident: ref110 article-title: Cross-domain multitask learning with latent probit models publication-title: Proc 29th Int Conf Mach Learn – start-page: 937 year: 2007 ident: ref122 article-title: Semi-supervised multitask learning publication-title: Proc Int Conf Neural Inf Process – ident: ref264 doi: 10.1214/09-AOS776 – ident: ref2 doi: 10.1017/9781139061773 – ident: ref19 doi: 10.1007/s11263-014-0767-8 – start-page: 525 year: 2018 ident: ref115 article-title: Multi-task learning as multi-objective optimization publication-title: Proc Int Conf Neural Inf Process – ident: ref174 doi: 10.1145/2939672.2939834 – year: 2009 ident: ref178 article-title: Online multi-task learning with hard constraints publication-title: Proc 22nd Conf Learn Theory – ident: ref121 doi: 10.1109/TKDE.2017.2657624 – ident: ref184 doi: 10.24963/ijcai.2017/253 – ident: ref100 doi: 10.1145/2020408.2020423 – start-page: 46 year: 2010 ident: ref42 article-title: Learning multiple tasks using manifold regularization publication-title: Proc Adv Neural Inf Process Syst – start-page: 343 year: 2013 ident: ref12 article-title: Sparse coding for multitask and transfer learning publication-title: Proc 30th Int Conf Mach Learn – start-page: 1896 year: 2013 ident: ref96 article-title: Heterogeneous-neighborhood-based multi-task local learning algorithms publication-title: Proc Int Conf Neural Inf Process – start-page: 1444 year: 2013 ident: ref113 article-title: Multilinear multitask learning publication-title: Proc 30th Int Conf Mach Learn – start-page: 1427 year: 2008 ident: ref203 article-title: Transferring multi-device localization models using latent multi-task learning publication-title: Proc AAAI Conf Artif Intell – ident: ref57 doi: 10.1145/1390156.1390253 – start-page: 4851 year: 2017 ident: ref146 article-title: Multi-task learning for contextual bandits publication-title: Proc Int Conf Neural Inf Process – ident: ref166 doi: 10.1145/2339530.2339617 – start-page: 794 year: 2018 ident: ref117 article-title: Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks publication-title: Proc Int Conf Mach Learn – start-page: 946 year: 1996 ident: ref198 article-title: Multi-task learning for stock selection publication-title: Proc Int Conf Neural Inf Process – year: 2017 ident: ref156 article-title: Online multi-task learning using active sampling publication-title: Proc Int Conf Learn Representations Workshop – volume: 17 start-page: 1 year: 2016 ident: ref259 article-title: The benefit of multitask representation learning publication-title: J Mach Learn Res – year: 2006 ident: ref23 article-title: Multi-task feature selection – year: 2012 ident: ref66 article-title: Learning task grouping and overlap in multi-task learning publication-title: Proc 29th Int Conf Mach Learn – ident: ref127 doi: 10.1137/1.9781611974010.57 – ident: ref258 doi: 10.1609/aaai.v29i1.9558 – ident: ref239 doi: 10.1109/TITS.2016.2598356 – ident: ref134 doi: 10.1609/aaai.v25i1.7914 – ident: ref27 doi: 10.1145/2623330.2623641 – start-page: 1283 year: 2012 ident: ref60 article-title: Flexible modeling of latent task structures in multitask learning publication-title: Proc 29th Int Conf Mach Learn – ident: ref199 doi: 10.1109/CVPR.2013.61 – ident: ref211 doi: 10.1109/CVPR.2010.5539967 – ident: ref45 doi: 10.1609/aaai.v30i1.10261 – ident: ref241 doi: 10.1109/TKDE.2017.2662006 – ident: ref209 doi: 10.1109/ICCV.2015.383 – ident: ref133 doi: 10.1145/2747879 – ident: ref138 doi: 10.1109/TCYB.2014.2344015 – volume: 13 start-page: 1865 year: 2012 ident: ref255 article-title: Regularization techniques for learning with matrices publication-title: J Mach Learn Res – ident: ref17 doi: 10.1109/TBDATA.2016.2573280 – start-page: 1209 year: 2015 ident: ref136 article-title: Multi-task learning for subspace segmentation publication-title: Proc Int Conf Mach Learn – ident: ref85 doi: 10.1109/CVPR.2015.7298608 – start-page: 1306 year: 2010 ident: ref25 article-title: Adaptive multi-task lasso: With application to eQTL detection publication-title: Proc Int Conf Neural Inf Process – volume: 8 start-page: 35 year: 2007 ident: ref54 article-title: Multi-task learning for classification with Dirichlet process priors publication-title: J Mach Learn Res – volume: 6 start-page: 1817 year: 2005 ident: ref40 article-title: A framework for learning predictive structures from multiple tasks and unlabeled data publication-title: J Mach Learn Res – start-page: 167 year: 2012 ident: ref171 article-title: Inductive transfer for Bayesian network structure learning publication-title: Proc Mach Learn – start-page: 142 year: 2009 ident: ref210 article-title: Boosted multi-task learning for face verification with applications to web image and video search publication-title: Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit – start-page: 2807 year: 2017 ident: ref130 article-title: Multi-task learning with labeled and unlabeled tasks publication-title: Proc Int Conf Mach Learn – start-page: 4773 year: 2019 ident: ref160 article-title: Adaptive auxiliary task weighting for reinforcement learning publication-title: Proc Int Conf Neural Inf Process – start-page: 3185 year: 2012 ident: ref92 article-title: Simultaneously leveraging output and task structures for multiple-output regression publication-title: Proc 25th Int Conf Neural Inf Process Syst – ident: ref123 doi: 10.1109/TPAMI.2008.296 – start-page: 1406 year: 2018 ident: ref158 article-title: IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures publication-title: Proc Int Conf Mach Learn – start-page: 4427 year: 2017 ident: ref189 article-title: Federated multi-task learning publication-title: Proc Int Conf Neural Inf Process – ident: ref188 doi: 10.1145/3097983.3098152 – ident: ref230 doi: 10.1109/ICDM.2015.68 – start-page: 2559 year: 2010 ident: ref37 article-title: Probabilistic multi-task feature selection publication-title: Proc Int Conf Neural Inf Process – start-page: 1531 year: 2012 ident: ref105 article-title: A convex feature learning formulation for latent task structure discovery publication-title: Proc 29th Int Conf Mach Learn – start-page: 2030 year: 2015 ident: ref53 article-title: A multitask point process predictive model publication-title: Proc Int Conf Mach Learn – ident: ref20 doi: 10.21437/Interspeech.2016-879 – start-page: 1475 year: 2012 ident: ref49 article-title: Learning multiple tasks using shared hypotheses publication-title: Proc 25th Int Conf Neural Inf Process Syst – start-page: 8921 year: 2018 ident: ref159 article-title: Distributed multitask reinforcement learning with quadratic convergence publication-title: Proc Int Conf Neural Inf Process – start-page: 940 year: 2012 ident: ref217 article-title: Sparse Bayesian multi-task learning for predicting cognitive outcomes from neuroimaging measures in Alzheimer's disease publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – start-page: 65 year: 2012 ident: ref102 article-title: Convex multitask learning with flexible task clusters publication-title: Proc 18th Int Conf Artif Intell Statist – volume: 11 start-page: 935 year: 2010 ident: ref262 article-title: On spectral learning publication-title: J Mach Learn Res – ident: ref141 doi: 10.1145/1273496.1273624 – ident: ref41 doi: 10.1145/1553374.1553392 – ident: ref124 doi: 10.1007/978-3-642-04174-7_40 – year: 2018 ident: ref162 article-title: Hierarchical and interpretable skill acquisition in multi-task reinforcement learning publication-title: Proc Int Conf Learn Representations – ident: ref212 doi: 10.1186/1471-2105-11-181 – volume: 12 start-page: 2415 year: 2011 ident: ref265 article-title: Union support recovery in multi-task learning publication-title: J Mach Learn Res – ident: ref140 doi: 10.24963/ijcai.2018/435 – ident: ref180 doi: 10.1109/TPAMI.2008.297 – ident: ref10 doi: 10.1007/s10994-007-5040-8 – ident: ref253 doi: 10.1145/1143844.1143900 – start-page: 1091 year: 2012 ident: ref173 article-title: Leveraging domain knowledge in multitask Bayesian network structure learning publication-title: Proc AAAI Conf Artif Intell – start-page: 794 year: 2015 ident: ref18 article-title: Multi-domain dialog state tracking using recurrent neural networks publication-title: Proc Annual Meeting of the Assoc Computational Linguistics – ident: ref201 doi: 10.1109/ICASSP.2015.7178780 – ident: ref149 doi: 10.24963/ijcai.2019/505 – start-page: 964 year: 2010 ident: ref78 article-title: Multi-task learning using generalized $t$t process publication-title: Proc 13th Int Conf Artif Intell Statist – ident: ref246 doi: 10.1089/cmb.2016.0201 – ident: ref250 doi: 10.1613/jair.731 – start-page: 792 year: 2005 ident: ref8 article-title: Radial basis function network for multi-task learning publication-title: Proc Int Conf Neural Inf Process – start-page: 521 year: 2011 ident: ref62 article-title: Learning with whom to share in multi-task feature learning publication-title: Proc 28th Int Conf Mach Learn – ident: ref44 doi: 10.1137/090763184 – start-page: 49 year: 2011 ident: ref83 article-title: Learning output kernels with block coordinate descent publication-title: Proc 28th Int Conf Mach Learn – ident: ref222 doi: 10.1109/TIP.2011.2169274 – start-page: 737 year: 2007 ident: ref72 article-title: Multi-task learning via conic programming publication-title: Proc Int Conf Neural Inf Process – start-page: 1 year: 2020 ident: ref161 article-title: Sharing knowledge in multi-task deep reinforcement learning publication-title: Proc Int Conf Learn Representations – ident: ref202 doi: 10.21437/Interspeech.2015-659 – ident: ref139 doi: 10.1109/TNNLS.2016.2521602 – volume: 13 start-page: 2773 year: 2012 ident: ref107 article-title: Multi-task regression using minimal penalties publication-title: J Mach Learn Res – start-page: 1103 year: 2007 ident: ref52 article-title: Robust multi-task learning with t-processes publication-title: Proc 24th Int Conf Mach Learn – ident: ref235 doi: 10.1007/978-0-387-85774-9_8 – year: 2018 ident: ref157 article-title: Learning to multi-task by active sampling publication-title: Proc Int Conf Learn Representations – start-page: 2690 year: 2011 ident: ref75 article-title: Hierarchical multitask structured output learning for large-scale sequence segmentation publication-title: Proc 24th Int Conf Neural Inf Process Syst – ident: ref129 doi: 10.1109/ICDM.2016.0035 – ident: ref204 doi: 10.1145/1390156.1390177 – ident: ref34 doi: 10.1007/978-1-4419-9011-2 – start-page: 3644 year: 2014 ident: ref46 article-title: Spectral $k$k-support norm regularization publication-title: Proc 27th Int Conf Neural Inf Process Syst – start-page: 733 year: 2010 ident: ref79 article-title: A convex formulation for learning task relationships in multi-task learning publication-title: Proc 26th Conf Uncertainty Artif Intell – volume: 6 start-page: 615 year: 2005 ident: ref71 article-title: Learning multiple tasks with kernel methods publication-title: J Mach Learn Res – start-page: 1867 year: 2010 ident: ref70 article-title: Large margin multi-task metric learning publication-title: Proc Int Conf Neural Inf Process – ident: ref168 doi: 10.1109/TKDE.2016.2603983 – ident: ref63 doi: 10.1609/aaai.v29i1.9581 – year: 2015 ident: ref64 article-title: Convex multi-task learning by clustering publication-title: Proc Artif Intell Statist – ident: ref215 doi: 10.1093/bioinformatics/btq191 – ident: ref257 doi: 10.1007/978-3-319-24486-0_13 – start-page: 746 year: 2013 ident: ref38 article-title: Learning feature selection dependencies in multi-task learning publication-title: Proc Int Conf Neural Inf Process – ident: ref56 doi: 10.1109/ICASSP.2011.5946926 – year: 2016 ident: ref207 article-title: Multi-task sequence to sequence learning publication-title: Proc Int Conf Learn Representations – ident: ref4 doi: 10.1016/j.neunet.2019.01.012 – ident: ref9 doi: 10.1007/s10994-008-5088-0 – volume: 10 start-page: 1131 year: 2009 ident: ref142 article-title: Multi-task reinforcement learning in partially observable stochastic environments publication-title: J Mach Learn Res – ident: ref185 doi: 10.1609/aaai.v33i01.33015636 – year: 2017 ident: ref248 article-title: A survey on multi-task learning – ident: ref169 doi: 10.1109/TCYB.2015.2403356 – ident: ref3 doi: 10.1109/TKDE.2013.39 – start-page: 2151 year: 2009 ident: ref6 article-title: Heterogeneous multitask learning with joint sparsity constraints publication-title: Proc Int Conf Neural Inf Process – ident: ref190 doi: 10.1007/s10994-017-5676-y – ident: ref200 doi: 10.1093/bioinformatics/btq394 – year: 2007 ident: ref11 article-title: A spectral regularization framework for multi-task structure learning publication-title: Proc Int Conf Neural Inf Process – ident: ref206 doi: 10.1109/TMM.2015.2477680 – start-page: 153 year: 2007 ident: ref76 article-title: Multi-task Gaussian process prediction publication-title: Proc Int Neural Inf Process Syst – ident: ref175 doi: 10.1109/ICDM.2015.130 – start-page: 1847 year: 2017 ident: ref155 article-title: Scalable multitask policy gradient reinforcement learning publication-title: Proc AAAI Conf Artif Intell – start-page: 2357 year: 2016 ident: ref137 article-title: Self-adapted multi-task clustering publication-title: Proc Int Joint Conf Artif Intell – volume: 7 start-page: 117 year: 2006 ident: ref251 article-title: Bounds for linear multi-task learning publication-title: J Mach Learn Res – start-page: 447 year: 2010 ident: ref172 article-title: Multi-task learning of Gaussian graphical models publication-title: Proc Int Conf Mach Learn – ident: ref33 doi: 10.1609/aaai.v28i1.9009 – start-page: 1277 year: 2012 ident: ref223 article-title: High-order multi-task feature learning to identify longitudinal phenotypic markers for Alzheimer's disease progression prediction publication-title: Proc Adv Neural Inf Process Syst – ident: ref183 doi: 10.1109/TKDE.2017.2703106 – ident: ref226 doi: 10.1109/CVPR.2010.5539975 – start-page: 3875 year: 2020 ident: ref164 article-title: Bootstrap latent-predictive representations for multitask reinforcement learning publication-title: Proc Int Conf Mach Learn – ident: ref131 doi: 10.1609/aaai.v24i1.7674 – start-page: 230 year: 2016 ident: ref97 article-title: Asymmetric multi-task learning based on task relatedness and loss publication-title: Proc Int Conf Mach Learn – start-page: 3017 year: 2017 ident: ref147 article-title: Hierarchy through composition with multitask LMDPs publication-title: Proc Int Conf Mach Learn – start-page: 5 year: 2014 ident: ref144 article-title: Sparse multi-task reinforcement learning publication-title: Proc Int Conf Neural Inf Process – ident: ref87 doi: 10.1609/aaai.v31i1.10820 – ident: ref126 doi: 10.1137/1.9781611973440.22 – start-page: 643 year: 2011 ident: ref181 article-title: Online learning of multiple tasks and their relationships publication-title: Proc Int Conf Artif Intell Statist – ident: ref249 doi: 10.1145/225298.225336 – ident: ref191 doi: 10.1145/1553374.1553516 – start-page: 2066 year: 2012 ident: ref106 article-title: Geodesic flow kernel for unsupervised domain adaptation publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – start-page: 745 year: 2008 ident: ref61 article-title: Clustered multi-task learning: A convex formulation publication-title: Proc 18th Int Conf Artif Intell Statist – start-page: 1593 year: 2017 ident: ref95 article-title: Learning multiple tasks with multilinear relationship networks publication-title: Proc 31st Int Conf Neural Inf Process Syst – ident: ref242 doi: 10.1093/bioinformatics/btt245 – start-page: 1957 year: 2010 ident: ref112 article-title: Multitask learning without label correspondences publication-title: Proc 23rd Int Conf Neural Inf Process Syst – ident: ref252 doi: 10.1007/11776420_8 – volume: 8 start-page: 2233 year: 2007 ident: ref177 article-title: Online learning of multiple tasks with a shared loss publication-title: J Mach Learn Res – ident: ref80 doi: 10.1145/2538028 – ident: ref232 doi: 10.1007/978-3-642-12683-3_34 – year: 2017 ident: ref67 article-title: Deep multi-task representation learning: A tensor factorisation approach publication-title: Proc Int Conf Mach Representations – ident: ref228 doi: 10.1109/ICCV.2015.430 – ident: ref187 doi: 10.1145/3097983.3098136 – ident: ref51 doi: 10.1145/1102351.1102479 – start-page: 543 year: 2010 ident: ref35 article-title: Tree-guided group lasso for multi-task regression with structured sparsity publication-title: Proc 27th Int Conf Mach Learn – ident: ref219 doi: 10.1093/bioinformatics/btq181 – ident: ref218 doi: 10.1093/bioinformatics/btw249 – year: 2011 ident: ref68 article-title: Clustered multi-task learning via alternating structure optimization publication-title: Proc Int Conf Neural Inf Process – start-page: 5776 year: 2018 ident: ref108 article-title: Learning to multitask publication-title: Proc 32nd Int Conf Neural Inf Process Syst – start-page: 423 year: 2013 ident: ref90 article-title: Multi-task learning with Gaussian matrix generalized inverse Gaussian model publication-title: Proc Int Conf Mach Learn – volume: 10 start-page: 2507 year: 2009 ident: ref261 article-title: When is there a representer theorem? Vector versus matrix regularizers publication-title: J Mach Learn Res – ident: ref238 doi: 10.1609/aaai.v27i1.8577 – year: 2016 ident: ref151 article-title: Actor-mimic: Deep multitask and transfer reinforcement learning publication-title: Proc Int Conf Learn Representations – start-page: 2550 year: 2010 ident: ref88 article-title: Learning multiple tasks with a sparse matrix-normal penalty publication-title: Proc 23rd Int Conf Neural Inf Process Syst – year: 2017 ident: ref47 article-title: Trace norm regularised deep multi-task learning publication-title: Proc 5th Int Conf Learn Representation Workshop Track – start-page: 1548 year: 2015 ident: ref84 article-title: Convex learning of multiple tasks and their structure publication-title: Proc 32nd Int Conf Mach Learn – ident: ref22 doi: 10.1109/CVPR.2016.433 – start-page: 489 year: 1996 ident: ref48 article-title: Discovering structure in multiple learning tasks: The TC algorithm publication-title: Proc 13th Int Conf Mach Learn – ident: ref132 doi: 10.1609/aaai.v27i1.8557 – ident: ref119 doi: 10.1145/2783258.2783377 – ident: ref111 doi: 10.1007/s10994-013-5379-y – start-page: 4303 year: 2016 ident: ref182 article-title: Adaptive smoothed online multi-task learning publication-title: Proc Int Conf Neural Inf Process – ident: ref81 doi: 10.1007/978-3-642-33460-3_50 – ident: ref65 doi: 10.1109/TPAMI.2015.2452911 – start-page: 1755 year: 2011 ident: ref89 article-title: Sparse Bayesian multi-task learning publication-title: Proc Int Conf Neural Inf Process – start-page: 1637 year: 2009 ident: ref128 article-title: Active learning for semi-supervised multi-task learning publication-title: Proc IEEE Int Conf Acoust Speech Signal Process – start-page: 1466 year: 2013 ident: ref93 article-title: It is all in the noise: Efficient multi-task Gaussian process inference with structured residuals publication-title: Proc 26th Int Conf Neural Inf Process Syst – ident: ref245 doi: 10.1109/ICCV.2013.150 – volume: 7 start-page: 1 year: 2016 ident: ref94 article-title: Multi-task sparse structure learning with Gaussian copula models publication-title: J Mach Learn Res – ident: ref213 doi: 10.1145/2396761.2398508 – ident: ref74 doi: 10.1162/NECO_a_00844 – ident: ref196 doi: 10.21437/Interspeech.2015-265 – start-page: 37 year: 2013 ident: ref103 article-title: Hierarchical regularization cascade for joint learning publication-title: Proc Int Conf Mach Learn – start-page: 1189 year: 2015 ident: ref86 article-title: Efficient output kernel learning for multiple tasks publication-title: Proc Int Conf Neural Process Syst – start-page: 751 year: 2016 ident: ref186 article-title: Distributed multi-task learning publication-title: Proc Int Conf Artif Intell Statist – ident: ref69 doi: 10.1145/1014052.1014067 – start-page: 1917 year: 2013 ident: ref91 article-title: Learning high-order task relationships in multi-task learning publication-title: Proc 23rd Int Joint Conf Artif Intell – ident: ref58 doi: 10.1145/1273496.1273583 – volume: 4 start-page: 83 year: 2003 ident: ref50 article-title: Task clustering and gating for Bayesian multitask learning publication-title: J Mach Learn Res – start-page: 166 year: 2017 ident: ref145 article-title: Modular multitask reinforcement learning with policy sketches publication-title: Proc Int Conf Mach Learn – start-page: 2681 year: 2017 ident: ref153 article-title: Deep decentralized multi-task multi-agent reinforcement learning under partial observability publication-title: Proc Int Conf Mach Learn – ident: ref243 doi: 10.1093/bioinformatics/bty457 – ident: ref99 doi: 10.1145/1835804.1835952 – ident: ref197 doi: 10.1145/1645953.1646169 – ident: ref254 doi: 10.1007/s10994-007-5043-5 – ident: ref59 doi: 10.1109/TSP.2008.924798 – start-page: 4499 year: 2017 ident: ref154 article-title: Distral: Robust multitask reinforcement learning publication-title: Proc Int Conf Neural Inf Process – ident: ref224 doi: 10.1145/1390156.1390159 – start-page: 1747 year: 2015 ident: ref28 article-title: Safe screening for multi-task feature learning with multiple data matrices publication-title: Proc Int Conf Mach Learn – ident: ref195 doi: 10.1109/ICASSP.2015.7178814 – volume: 15 start-page: 3621 year: 2014 ident: ref73 article-title: Revisiting Stein's paradox: Multi-task averaging publication-title: J Mach Learn Res – volume: 11 start-page: 2901 year: 2010 ident: ref179 article-title: Linear algorithms for online multitask classification publication-title: J Mach Learn Res – start-page: 988 year: 2010 ident: ref36 article-title: Exclusive lasso for multi-task feature selection publication-title: Proc 13th Int Conf Artif Intell Statist – start-page: 557 year: 2011 ident: ref214 article-title: Sparse multi-task regression and feature selection to identify brain imaging predictors for memory performance publication-title: Proc IEEE Int Conf Comput Vis – ident: ref120 doi: 10.1145/2939672.2939857 – ident: ref216 doi: 10.1145/2020408.2020549 – start-page: 725 year: 2010 ident: ref233 article-title: Multi-domain collaborative filtering publication-title: Proc Conf Uncertainty Artif Intell – ident: ref109 doi: 10.1609/aaai.v25i1.7909 – ident: ref170 doi: 10.1137/1.9781611975673.2 – year: 2009 ident: ref263 article-title: Taking advantage of sparsity in multi-task learning publication-title: Proc Annu Conf Learn Theory – start-page: 676 year: 2015 ident: ref208 article-title: Rotating your face using multi-task deep neural network publication-title: Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit – start-page: 25 year: 2011 ident: ref165 article-title: A graph-based framework for multi-task multi-view learning publication-title: Proc Int Conf Mach Learn – ident: ref247 doi: 10.1109/TPAMI.2017.2679002 – start-page: 17 year: 2010 ident: ref225 article-title: Multitask learning for brain-computer interfaces publication-title: Mach Learn Res – ident: ref7 doi: 10.1145/1390156.1390164 – start-page: 964 year: 2010 ident: ref98 article-title: A dirty model for multi-task learning publication-title: Proc 23rd Int Conf Neural Inf Process Syst – start-page: 599 year: 2010 ident: ref143 article-title: Bayesian multi-task reinforcement learning publication-title: Proc Int Conf Mach Learn – start-page: 1585 year: 2005 ident: ref43 article-title: Learning multiple related tasks using latent independent component analysis publication-title: Proc Int Conf Neural Inf Process – ident: ref55 doi: 10.1145/1273496.1273630 – start-page: 1073 year: 2015 ident: ref39 article-title: A probabilistic model for dirty multi-task feature selection publication-title: Proc Int Conf Mach Learn – ident: ref1 doi: 10.1023/A:1007379606734 – ident: ref237 doi: 10.1145/2556195.2556264 – start-page: 2825 year: 2014 ident: ref114 article-title: Multitask learning meets tensor factorization: Task imputation via convex optimization publication-title: Proc 27th Int Conf Neural Inf Process Syst – year: 2020 ident: ref116 article-title: Gradient surgery for multi-task learning publication-title: Proc Int Conf Neural Inf Process – ident: ref193 doi: 10.1007/s11263-012-0582-z – volume: 19 start-page: 1 year: 2018 ident: ref260 article-title: Local Rademacher complexity-based learning guarantees for multi-task learning publication-title: J Mach Learn Res – ident: ref221 doi: 10.1137/1.9781611974348.74 – ident: ref240 doi: 10.1186/1471-2105-12-389 – start-page: 55 year: 2013 ident: ref256 article-title: Excess risk bounds for multitask learning with trace norm regularization publication-title: Proc Annu Conf Learn Theory
SSID	ssj0008781
Score	2.7596405
SecondaryResourceType	review_article
Snippet	Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	5586
SubjectTerms	Algorithms artificial intelligence Classification algorithms Clustering Cognitive tasks Computational modeling Data models Machine learning Modelling Multi-task learning Performance enhancement Supervised learning Task analysis Training Transfer learning
Title	A Survey on Multi-Task Learning
URI	https://ieeexplore.ieee.org/document/9392366 https://www.proquest.com/docview/2734385688
Volume	34
WOSCitedRecordID	wos000880645200003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library Online customDbUrl: eissn: 1558-2191 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0008781 issn: 1041-4347 databaseCode: RIE dateStart: 19890101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB6seNCDj6pYn3vwJK7ubrJ5HIu2CIIIVuhtySYTEWUrfYH_3k2aLoIieMshgfBNJpNJMt8HcK6FNnmuSMxKrWPKNMaKcxtnKRNWKGswUV5sgj88iOFQPq7AZVMLg4j-8xleuaZ_yzcjPXNXZdeyDuaEsRa0OOeLWq1m1xXcC5LW2UWdExHKwwtmmsjrwf1tr84Es_TKLfBsqY8VYpAXVfmxE_vw0t_638S2YTMcI6Puwu47sIJVG7aWEg1R8Ng2bHzjG9yFs270NBvP8TMaVZEvvY0HavIWBZLVlz147vcGN3dxUEiIdR2mp7GWlgk0KLQ0MtEJyYnJSya4LLXSpqQJYu1zlklam4LyUqYokzJXKDNLMkX2YbUaVXgAkU0JM5wwRamhGTVKESTcSVuV2prMdiBZYlboQB_uVCzeC59GJLJwMBcO5iLA3IGLZsjHgjvjr867DtemY4C0A8dLwxTBuyaFo-QhImdCHP4-6gjWM1em4L-dHMPqdDzDE1jT8-nrZHzqF84XNQW_AA
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3JSgQxEC3cQD24i-PaB09iO91JOstRXFDUQXAEb006qYgoMzKL4N_byWQGQRG85ZBAeJVKpZLUewCHRhpbFJqmvDImZdxgqoVwKcm5dFI7i5kOYhOi1ZJPT-p-Co4ntTCIGD6f4Ylvhrd82zVDf1XWVHUwp5xPw2zBGMlH1VqTfVeKIEla5xd1VkSZiG-Yeaaa7ZvzizoXJPmJX-JkrJAVo1CQVfmxF4cAc7n8v6mtwFI8SCanI8uvwhR21mB5LNKQRJ9dg8VvjIPrcHCaPAx7H_iZdDtJKL5N27r_mkSa1ecNeLy8aJ9dpVEjITV1oB6kRjku0aI0yqrMZLSgtqi4FKoy2tiKZYi11zmuWG0MJiqVo8qqQqMijhJNN2Gm0-3gFiQup9wKyjVjlhFmtaZIhRe3qoyzxDUgG2NWmkgg7nUs3sqQSGSq9DCXHuYywtyAo8mQ9xF7xl-d1z2uk44R0gbsjg1TRv_ql56Uh8qCS7n9-6gDmL9q392Wt9etmx1YIL5oIXxC2YWZQW-IezBnPgYv_d5-WERfVKjCRw
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+Survey+on+Multi-Task+Learning&rft.jtitle=IEEE+transactions+on+knowledge+and+data+engineering&rft.au=Zhang%2C+Yu&rft.au=Yang%2C+Qiang&rft.date=2022-12-01&rft.issn=1041-4347&rft.eissn=1558-2191&rft.volume=34&rft.issue=12&rft.spage=5586&rft.epage=5609&rft_id=info:doi/10.1109%2FTKDE.2021.3070203&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TKDE_2021_3070203
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1041-4347&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1041-4347&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1041-4347&client=summon