Informed Machine Learning - A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems

Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge into the training process which leads to the notion of informed machine learning . In this paper, we present a structure...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on knowledge and data engineering Ročník 35; číslo 1; s. 614 - 633
Hlavní autori: von Rueden, Laura, Mayer, Sebastian, Beckh, Katharina, Georgiev, Bogdan, Giesselbach, Sven, Heese, Raoul, Kirsch, Birgit, Pfrommer, Julius, Pick, Annika, Ramamurthy, Rajkumar, Walczak, Michal, Garcke, Jochen, Bauckhage, Christian, Schuecker, Jannis
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.01.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
ISSN:1041-4347, 1558-2191
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge into the training process which leads to the notion of informed machine learning . In this paper, we present a structured overview of various approaches in this field. We provide a definition and propose a concept for informed machine learning which illustrates its building blocks and distinguishes it from conventional machine learning. We introduce a taxonomy that serves as a classification framework for informed machine learning approaches. It considers the source of knowledge, its representation, and its integration into the machine learning pipeline. Based on this taxonomy, we survey related research and describe how different knowledge representations such as algebraic equations, logic rules, or simulation results can be used in learning systems. This evaluation of numerous papers on the basis of our taxonomy uncovers key methods in the field of informed machine learning.
AbstractList Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge into the training process which leads to the notion of informed machine learning . In this paper, we present a structured overview of various approaches in this field. We provide a definition and propose a concept for informed machine learning which illustrates its building blocks and distinguishes it from conventional machine learning. We introduce a taxonomy that serves as a classification framework for informed machine learning approaches. It considers the source of knowledge, its representation, and its integration into the machine learning pipeline. Based on this taxonomy, we survey related research and describe how different knowledge representations such as algebraic equations, logic rules, or simulation results can be used in learning systems. This evaluation of numerous papers on the basis of our taxonomy uncovers key methods in the field of informed machine learning.
Author Beckh, Katharina
Georgiev, Bogdan
Kirsch, Birgit
Schuecker, Jannis
Mayer, Sebastian
Bauckhage, Christian
Pick, Annika
Pfrommer, Julius
von Rueden, Laura
Heese, Raoul
Walczak, Michal
Giesselbach, Sven
Ramamurthy, Rajkumar
Garcke, Jochen
Author_xml – sequence: 1
  givenname: Laura
  orcidid: 0000-0002-7186-9753
  surname: von Rueden
  fullname: von Rueden, Laura
  email: laura.von.rueden@iais.fraunhofer.de
  organization: Fraunhofer IAIS, Institute for Intelligent Analysis and Information Systems, Sankt Augustin, Germany
– sequence: 2
  givenname: Sebastian
  orcidid: 0000-0002-1909-7805
  surname: Mayer
  fullname: Mayer, Sebastian
  organization: Fraunhofer SCAI, Institute for Algorithms and Scientific Computing, Sankt Augustin, Germany
– sequence: 3
  givenname: Katharina
  orcidid: 0000-0002-7824-6647
  surname: Beckh
  fullname: Beckh, Katharina
  organization: Fraunhofer IAIS, Institute for Intelligent Analysis and Information Systems, Sankt Augustin, Germany
– sequence: 4
  givenname: Bogdan
  orcidid: 0000-0002-4687-768X
  surname: Georgiev
  fullname: Georgiev, Bogdan
  organization: Fraunhofer IAIS, Institute for Intelligent Analysis and Information Systems, Sankt Augustin, Germany
– sequence: 5
  givenname: Sven
  orcidid: 0000-0002-2691-1406
  surname: Giesselbach
  fullname: Giesselbach, Sven
  organization: Fraunhofer IAIS, Institute for Intelligent Analysis and Information Systems, Sankt Augustin, Germany
– sequence: 6
  givenname: Raoul
  orcidid: 0000-0001-7479-3339
  surname: Heese
  fullname: Heese, Raoul
  organization: Fraunhofer ITWM, Institute for Industrial Mathematics, Kaiserslautern, Germany
– sequence: 7
  givenname: Birgit
  orcidid: 0000-0002-4888-4947
  surname: Kirsch
  fullname: Kirsch, Birgit
  organization: Fraunhofer IAIS, Institute for Intelligent Analysis and Information Systems, Sankt Augustin, Germany
– sequence: 8
  givenname: Julius
  orcidid: 0000-0002-4204-6758
  surname: Pfrommer
  fullname: Pfrommer, Julius
  organization: Fraunhofer IOSB, Institute for Optronics, System Technologies and Image Exploitation, Karlsruhe, Germany
– sequence: 9
  givenname: Annika
  orcidid: 0000-0002-9290-2487
  surname: Pick
  fullname: Pick, Annika
  organization: Fraunhofer IAIS, Institute for Intelligent Analysis and Information Systems, Sankt Augustin, Germany
– sequence: 10
  givenname: Rajkumar
  orcidid: 0000-0003-4440-7032
  surname: Ramamurthy
  fullname: Ramamurthy, Rajkumar
  organization: Fraunhofer IAIS, Institute for Intelligent Analysis and Information Systems, Sankt Augustin, Germany
– sequence: 11
  givenname: Michal
  orcidid: 0000-0001-5151-7462
  surname: Walczak
  fullname: Walczak, Michal
  organization: Fraunhofer ITWM, Institute for Industrial Mathematics, Kaiserslautern, Germany
– sequence: 12
  givenname: Jochen
  orcidid: 0000-0002-8334-3695
  surname: Garcke
  fullname: Garcke, Jochen
  organization: Fraunhofer SCAI, Institute for Algorithms and Scientific Computing, Sankt Augustin, Germany
– sequence: 13
  givenname: Christian
  orcidid: 0000-0001-6615-2128
  surname: Bauckhage
  fullname: Bauckhage, Christian
  organization: Fraunhofer IAIS, Institute for Intelligent Analysis and Information Systems, Sankt Augustin, Germany
– sequence: 14
  givenname: Jannis
  orcidid: 0000-0001-6203-1126
  surname: Schuecker
  fullname: Schuecker, Jannis
  organization: Fraunhofer IAIS, Institute for Intelligent Analysis and Information Systems, Sankt Augustin, Germany
BookMark eNp9kEFPwjAUxxujiYB-AOOliedhu25reySISsBoAp6bsr1iCWuxG-q-vVsgmnjw9N7h9_u_vH8fnTrvAKErSoaUEnm7nN1NhjGJ6ZARLgXLTlCPpqmIYirpabuThEYJS_g56lfVhhAiuKA9ZKbO-FBCgZ90_mYd4Dno4Kxb4wiP8FJ_eefLBmtX4MU-fECDvcFTV8M66LrDXoL1Ac-c_9xCsQZsXe1_QxZNVUNZXaAzo7cVXB7nAL3eT5bjx2j-_DAdj-ZRzlhWR0UiuWGMJSKNJddaC8bylTawygQ3plu1SIuCmVynebEyiRCUmJgClzoXBRugm0PuLvj3PVS12vh9cO1JFfOEZ5RQzlqKH6g8-KoKYFRu6_Yb7-qg7VZRorpSVVeq6kpVx1Jbk_4xd8GWOjT_OtcHxwLADy-TWEqRsm-o_4Xl
CODEN ITKEEH
CitedBy_id crossref_primary_10_1177_14727978251324146
crossref_primary_10_1016_j_apenergy_2022_119806
crossref_primary_10_1038_s41598_025_15289_x
crossref_primary_10_1109_TKDE_2025_3538618
crossref_primary_10_1515_nanoph_2022_0815
crossref_primary_10_1109_TIA_2025_3559048
crossref_primary_10_1016_j_seta_2022_102326
crossref_primary_10_1109_TCSS_2024_3404921
crossref_primary_10_1007_s10845_022_01999_w
crossref_primary_10_1002_gamm_202100003
crossref_primary_10_1016_j_mechmat_2024_105141
crossref_primary_10_1109_TAI_2022_3227225
crossref_primary_10_1109_TGRS_2024_3506058
crossref_primary_10_1109_TNSRE_2022_3226860
crossref_primary_10_3389_fams_2024_1355726
crossref_primary_10_1002_cctc_202200355
crossref_primary_10_1007_s11740_022_01115_0
crossref_primary_10_1155_2022_4109070
crossref_primary_10_1109_TKDE_2025_3579716
crossref_primary_10_1063_5_0253146
crossref_primary_10_1016_j_knosys_2024_112202
crossref_primary_10_1007_s10845_022_01975_4
crossref_primary_10_1016_j_trc_2021_103010
crossref_primary_10_1109_TCDS_2024_3422873
crossref_primary_10_1016_j_physd_2024_134152
crossref_primary_10_1109_TMC_2025_3552538
crossref_primary_10_1016_j_conbuildmat_2023_134809
crossref_primary_10_1080_08839514_2025_2506788
crossref_primary_10_1016_j_rineng_2023_101023
crossref_primary_10_1051_matecconf_202439201126
crossref_primary_10_1007_s10064_024_04001_4
crossref_primary_10_3389_frai_2023_1066049
crossref_primary_10_1016_j_neunet_2023_06_028
crossref_primary_10_1038_s41524_022_00810_x
crossref_primary_10_1109_ACCESS_2021_3137341
crossref_primary_10_1063_5_0284425
crossref_primary_10_1109_TMTT_2023_3343514
crossref_primary_10_1016_j_fcr_2025_109912
crossref_primary_10_1063_5_0232675
crossref_primary_10_1007_s12065_024_01007_5
crossref_primary_10_1016_j_energy_2025_137268
crossref_primary_10_1007_s11042_024_19084_0
crossref_primary_10_1109_LRA_2022_3186769
crossref_primary_10_1016_j_jcmds_2024_100107
crossref_primary_10_1109_JIOT_2024_3359277
crossref_primary_10_1360_SSTe_2025_0096
crossref_primary_10_1162_tacl_a_00440
crossref_primary_10_1016_j_psep_2023_04_008
crossref_primary_10_1007_s11440_024_02384_y
crossref_primary_10_1016_j_matdes_2025_113737
crossref_primary_10_1109_TCYB_2025_3539990
crossref_primary_10_1515_teme_2022_0027
crossref_primary_10_1016_j_knosys_2025_112979
crossref_primary_10_1038_s41524_022_00884_7
crossref_primary_10_1007_s11071_024_09674_w
crossref_primary_10_1109_TPAMI_2024_3483273
crossref_primary_10_1093_biomethods_bpac005
crossref_primary_10_1515_polyeng_2024_0228
crossref_primary_10_1109_ACCESS_2023_3238872
crossref_primary_10_1109_JSAC_2023_3322766
crossref_primary_10_1016_j_matt_2022_11_018
crossref_primary_10_1088_2399_6528_ace416
crossref_primary_10_1109_TIM_2025_3579835
crossref_primary_10_3389_frai_2025_1485489
crossref_primary_10_1016_j_eswa_2022_116503
crossref_primary_10_1080_17445302_2023_2231207
crossref_primary_10_1109_TMI_2024_3412935
crossref_primary_10_1109_TKDE_2024_3389668
crossref_primary_10_1007_s11786_025_00603_7
crossref_primary_10_1109_JSTARS_2023_3270498
crossref_primary_10_1007_s00464_024_10958_w
crossref_primary_10_1002_hyp_70065
crossref_primary_10_1016_j_epsr_2024_110677
crossref_primary_10_1016_j_jrmge_2024_09_034
crossref_primary_10_1109_TII_2023_3247008
crossref_primary_10_3389_fsysb_2024_1407994
crossref_primary_10_1016_j_eswa_2022_119282
crossref_primary_10_1109_ACCESS_2023_3287397
crossref_primary_10_1109_TCPMT_2025_3589029
crossref_primary_10_1007_s10489_022_04310_9
crossref_primary_10_1016_j_procs_2025_01_066
crossref_primary_10_1016_j_procs_2025_01_065
crossref_primary_10_1016_j_procs_2025_01_067
crossref_primary_10_1515_zwf_2024_0154
crossref_primary_10_1109_JIOT_2024_3368516
crossref_primary_10_1007_s00202_025_02981_4
crossref_primary_10_3103_S0027134924702060
crossref_primary_10_1109_TSM_2025_3576269
crossref_primary_10_1109_TPEL_2024_3370690
crossref_primary_10_1109_TBME_2024_3477275
crossref_primary_10_1109_TII_2022_3224973
crossref_primary_10_1109_TNNLS_2023_3347453
crossref_primary_10_1049_htl2_70012
crossref_primary_10_1016_j_paerosci_2022_100849
crossref_primary_10_1088_3050_2454_adcef2
crossref_primary_10_1145_3609483
crossref_primary_10_3390_en14227572
crossref_primary_10_1080_00295639_2022_2107864
crossref_primary_10_1088_1742_5468_ac3a7f
crossref_primary_10_1007_s00502_024_01234_9
crossref_primary_10_1109_TKDE_2025_3556367
crossref_primary_10_1109_TCSVT_2023_3319633
crossref_primary_10_1007_s00163_024_00442_w
crossref_primary_10_1007_s10489_024_05746_x
crossref_primary_10_1016_j_ynexs_2024_100003
crossref_primary_10_1109_TPEL_2022_3176468
crossref_primary_10_1109_JSEN_2023_3347265
crossref_primary_10_1109_TGRS_2025_3527009
crossref_primary_10_1515_zwf_2024_1039
crossref_primary_10_4018_JGIM_331755
crossref_primary_10_1186_s12859_023_05262_8
crossref_primary_10_1109_TIV_2023_3325300
crossref_primary_10_1371_journal_pone_0279876
crossref_primary_10_1016_j_ress_2021_108119
crossref_primary_10_1016_j_array_2025_100393
crossref_primary_10_1016_j_procir_2023_06_141
crossref_primary_10_1109_TLT_2023_3348690
crossref_primary_10_1140_epje_s10189_023_00269_8
crossref_primary_10_1007_s10845_022_01973_6
crossref_primary_10_1016_j_specom_2022_11_005
crossref_primary_10_3233_SW_223228
crossref_primary_10_1016_j_pacfin_2024_102511
crossref_primary_10_1109_TFUZZ_2024_3471187
crossref_primary_10_1109_TNNLS_2024_3475271
crossref_primary_10_3390_a14120345
crossref_primary_10_1088_1361_6501_ad4ab8
crossref_primary_10_1016_j_knosys_2024_111716
crossref_primary_10_1109_TCYB_2024_3487934
crossref_primary_10_1016_j_istruc_2025_108540
crossref_primary_10_3390_s21020501
crossref_primary_10_1007_s00466_023_02434_4
crossref_primary_10_3389_fpls_2022_980581
crossref_primary_10_1016_j_aei_2024_102843
crossref_primary_10_1016_j_procs_2025_01_082
crossref_primary_10_1016_j_ress_2022_108900
crossref_primary_10_1007_s11431_024_2765_2
crossref_primary_10_1007_s43681_025_00831_4
crossref_primary_10_1007_s43503_024_00025_7
crossref_primary_10_1016_j_mfglet_2024_09_181
crossref_primary_10_1038_s41598_021_04590_0
crossref_primary_10_1088_1361_6528_ad0986
crossref_primary_10_1109_ACCESS_2023_3265722
crossref_primary_10_1109_TII_2024_3438256
crossref_primary_10_1007_s10479_022_04692_6
crossref_primary_10_1145_3645103
crossref_primary_10_1007_s11633_022_1384_6
crossref_primary_10_3390_electronics11182850
crossref_primary_10_1016_j_enganabound_2023_02_040
crossref_primary_10_1016_j_chaos_2022_112866
crossref_primary_10_3390_s21134322
crossref_primary_10_1155_2022_2978380
crossref_primary_10_1016_j_buildenv_2025_113640
crossref_primary_10_1088_1361_6501_adb76c
crossref_primary_10_3389_fsufs_2024_1363744
crossref_primary_10_1016_j_jmapro_2025_02_057
crossref_primary_10_1515_auto_2022_0076
crossref_primary_10_1109_TWC_2023_3316197
crossref_primary_10_1016_j_rcim_2023_102545
crossref_primary_10_1016_j_ymssp_2023_110625
crossref_primary_10_1016_j_chemolab_2024_105131
crossref_primary_10_1057_s41261_024_00233_2
crossref_primary_10_1145_3609333
crossref_primary_10_1109_MRA_2022_3207664
crossref_primary_10_1016_j_patcog_2023_109397
crossref_primary_10_1038_s41598_024_56640_y
crossref_primary_10_1109_TFUZZ_2024_3369422
crossref_primary_10_1111_exsy_12959
crossref_primary_10_70322_ism_2025_10008
crossref_primary_10_1016_j_eswa_2025_126439
crossref_primary_10_1109_LSP_2024_3491013
crossref_primary_10_1016_j_energy_2023_128387
crossref_primary_10_1145_3575637_3575650
crossref_primary_10_1190_geo2022_0770_1
crossref_primary_10_1016_j_cor_2022_106124
crossref_primary_10_1109_MCG_2021_3130314
crossref_primary_10_1109_TSC_2024_3407588
crossref_primary_10_3758_s13428_023_02258_3
crossref_primary_10_1109_TASE_2024_3515839
crossref_primary_10_1177_23814683231218716
crossref_primary_10_1016_j_oceaneng_2022_112998
crossref_primary_10_3390_en15093304
crossref_primary_10_1109_TGRS_2024_3454201
crossref_primary_10_1109_ACCESS_2022_3221740
crossref_primary_10_3233_IDA_216460
crossref_primary_10_1017_jfm_2021_1045
Cites_doi 10.1007/978-3-030-30493-5_38
10.1109/DSAA49011.2020.00069
10.1007/978-3-662-44848-9_9
10.1038/nature14422
10.1007/s10994-013-5392-1
10.1038/nature16961
10.1007/978-3-642-35085-6_6
10.1016/j.jbi.2014.07.018
10.1007/s10994-013-5399-7
10.1017/jfm.2016.615
10.1016/j.ijar.2005.10.003
10.24963/ijcai.2018/643
10.3390/machines5010004
10.1016/j.ijmachtools.2006.04.007
10.1002/aic.690381003
10.1186/1752-0509-4-121
10.1109/VAST.2012.6400486
10.18653/v1/P16-1228
10.1609/aaai.v32i1.11757
10.1145/3386252
10.1109/22.643839
10.21468/SciPostPhys.5.3.028
10.1109/BIBM.2018.8621379
10.1016/j.ijar.2006.06.009
10.1016/j.neucom.2018.02.029
10.18653/v1/P18-1165
10.1007/s10472-009-9133-x
10.1109/BigData.2018.8621955
10.1002/0470018860.s00035
10.1109/MSP.2012.2205597
10.1007/s10994-012-5296-5
10.3115/1690219.1690287
10.1016/j.eswa.2016.02.050
10.1109/MSP.2017.2693418
10.1093/bioinformatics/btz199
10.1017/CBO9781107706804
10.1016/j.procir.2018.03.046
10.1038/s41586-018-0337-2
10.1023/A:1008328630915
10.1098/rsif.2017.0387
10.1007/978-3-540-70956-5_7
10.1109/CVPR.2017.758
10.1017/jfm.2016.803
10.1023/A:1023283917997
10.1109/ICRA.2018.8460528
10.1145/3191513
10.1016/j.artint.2015.08.011
10.1021/cm100795d
10.1007/978-3-031-01574-8
10.1016/j.jcp.2019.05.024
10.1145/2783258.2783365
10.1109/TNN.2008.2005188
10.1109/IROS.2017.8205961
10.1007/s10994-006-5833-1
10.1016/0004-3702(94)90105-8
10.1017/S0140525X16001837
10.1109/72.712178
10.1007/978-3-030-30484-3_48
10.18653/v1/P19-1139
10.1145/3097983.3098126
10.18653/v1/D19-1005
10.1103/PhysRevFluids.3.074602
10.1109/TVCG.2013.212
10.1002/9781405164863.ch3
10.1109/5.726787
10.18653/v1/N16-1018
10.1609/aaai.v31i1.10934
10.1109/TKDE.2017.2720168
10.1007/978-3-642-02906-6_16
10.1017/CBO9780511618796
10.24963/ijcai.2017/230
10.18653/v1/D16-1173
10.3115/v1/P15-1012
10.1561/9781680836233
10.1109/ICMLA.2017.00-37
10.1145/604045.604056
10.1080/01621459.2017.1285773
10.18653/v1/N19-1288
10.1109/CVPR.2017.10
10.1007/978-3-030-44584-3_43
10.18653/v1/P18-1004
10.1145/219717.219748
10.1007/BF00994016
10.1145/1597735.1597738
10.18653/v1/D18-1445
10.1016/j.neucom.2007.04.010
10.1016/j.jbi.2013.10.012
10.1007/s102080010030
10.1017/CBO9780511803161
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
ESBDL
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/TKDE.2021.3079836
DatabaseName IEEE Xplore (IEEE)
IEEE Xplore Open Access Journals
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 (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 1558-2191
EndPage 633
ExternalDocumentID 10_1109_TKDE_2021_3079836
9429985
Genre orig-research
GrantInformation_xml – fundername: Federal Ministry of Education and Research of Germany
  grantid: 01; S18038B
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
ESBDL
F5P
HZ~
IEDLZ
IFIPE
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
RXW
TAE
TN5
UHB
1OL
5VS
9M8
AAYXX
ABFSI
AETIX
AGSQL
AI.
AIBXA
ALLEH
CITATION
E.L
H~9
ICLAB
IFJZH
RNI
RZB
TAF
VH1
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c336t-d497f333485297aaa833cbafeb687ffcbafa85dd3fca5cdbf48810f21e79ac8d3
IEDL.DBID RIE
ISICitedReferencesCount 455
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000895445500045&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 08:10:14 EST 2025
Sat Nov 29 02:36:03 EST 2025
Tue Nov 18 22:11:18 EST 2025
Wed Aug 27 02:15:01 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c336t-d497f333485297aaa833cbafeb687ffcbafa85dd3fca5cdbf48810f21e79ac8d3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-7186-9753
0000-0002-8334-3695
0000-0001-5151-7462
0000-0002-7824-6647
0000-0001-6615-2128
0000-0002-2691-1406
0000-0002-9290-2487
0000-0002-1909-7805
0000-0002-4888-4947
0000-0001-7479-3339
0000-0002-4204-6758
0000-0003-4440-7032
0000-0001-6203-1126
0000-0002-4687-768X
OpenAccessLink https://ieeexplore.ieee.org/document/9429985
PQID 2747610173
PQPubID 85438
PageCount 20
ParticipantIDs proquest_journals_2747610173
crossref_primary_10_1109_TKDE_2021_3079836
ieee_primary_9429985
crossref_citationtrail_10_1109_TKDE_2021_3079836
PublicationCentury 2000
PublicationDate 2023-01-01
PublicationDateYYYYMMDD 2023-01-01
PublicationDate_xml – month: 01
  year: 2023
  text: 2023-01-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on knowledge and data engineering
PublicationTitleAbbrev TKDE
PublicationYear 2023
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
lutter (ref48) 2019
ref56
ref59
ref53
ref52
ref55
ref54
kahneman (ref29) 2011
wirtz (ref110) 2021
schmid (ref39) 2020
ref51
embar (ref145) 2018
ref50
bach (ref144) 2015
christiano (ref103) 2017
ref46
ref45
ref47
steinwart (ref134) 2008
kaplan (ref99) 2017
ref7
dulac-arnold (ref150) 2019
chang (ref83) 2007
ref4
ref6
ref5
ref100
chang (ref62) 2016
schiegg (ref77) 2012
ref35
lapidus (ref136) 2011
ref34
ref37
ref148
ref30
ref33
ref146
ref147
mikolov (ref121) 2013
ref38
castellano (ref95) 2007; 45
borboudakis (ref58) 2021
lerer (ref64) 2016
ref151
ref152
kalnay (ref129) 2003
ref23
ref26
raissi (ref20) 2017
ref22
ref21
schölkopf (ref72) 1998
bergman (ref82) 2019
fung (ref36) 2003
shrivastava (ref67) 2017
sachan (ref78) 2018
abu-mostafa (ref32) 2012
xu (ref11) 0
mrkši (ref87) 2016
brundage (ref8) 2020
lee (ref18) 2019
rai (ref65) 2019; 20
richardson (ref101) 2003
liang (ref81) 2018
ref13
devlin (ref119) 2018
schramowski (ref109) 2020
battaglia (ref24) 2018
ref15
machamer (ref27) 2008; 19
ref97
ref127
ref96
ref124
ref125
ref98
ref10
minsky (ref128) 1991; 12
ref17
kimmig (ref91) 2012
battaglia (ref14) 2016
ref19
yang (ref43) 2018
ref133
ref93
ref92
ref132
ref94
ref130
jiang (ref16) 2018
ref90
steup (ref25) 2018
janner (ref131) 2017
ref89
king (ref41) 2018
ref139
karpatne (ref12) 2017
ref137
ref86
ref138
ref85
ref135
ref88
kreutzer (ref149) 2020
jeong (ref42) 2015; 34
dong (ref143) 2018
krizhevsky (ref1) 2012
mcgarry (ref140) 1999; 2
ref84
ref141
ref80
ref79
ref106
ref107
ref75
ref104
ref74
ref105
belbute-peres (ref49) 2018
ref102
ref76
pajot (ref44) 2017
ref2
doshi-velez (ref153) 2017
garcez (ref142) 2020
dieleman (ref71) 2016
settles (ref126) 2009
ref111
ref112
ref73
cohen (ref70) 2016
ref68
gauch (ref31) 2003
ref117
garcez (ref114) 2019
ref69
ref118
ref115
ref63
ref116
ref113
fayyad (ref28) 1996; 17
bauckhage (ref40) 2018
roscher (ref9) 2019
rieger (ref108) 2019
conneau (ref3) 2016
ref60
ref122
ref123
ref120
ref61
du (ref66) 2018
References_xml – ident: ref35
  doi: 10.1007/978-3-030-30493-5_38
– year: 2016
  ident: ref64
  article-title: Learning physical intuition of block towers by example
– year: 2017
  ident: ref44
  article-title: Deep learning for physical processes: Incorporating prior scientific knowledge
– start-page: 84
  year: 2012
  ident: ref1
  article-title: Imagenet classification with deep convolutional neural networks
  publication-title: Proc Neural Inf Process Syst
– ident: ref125
  doi: 10.1109/DSAA49011.2020.00069
– ident: ref88
  doi: 10.1007/978-3-662-44848-9_9
– ident: ref17
  doi: 10.1038/nature14422
– ident: ref89
  doi: 10.1007/s10994-013-5392-1
– ident: ref4
  doi: 10.1038/nature16961
– start-page: 2990
  year: 2016
  ident: ref70
  article-title: Group equivariant convolutional networks
  publication-title: Proc Int Conf Mach Learn
– ident: ref116
  doi: 10.1007/978-3-642-35085-6_6
– ident: ref73
  doi: 10.1016/j.jbi.2014.07.018
– year: 2019
  ident: ref9
  article-title: Explainable machine learning for scientific insights and discoveries
– year: 2020
  ident: ref109
  article-title: Right for the wrong scientific reasons: Revising deep networks by interacting with their explanations
– year: 2016
  ident: ref3
  article-title: Very deep convolutional networks for text classification
– year: 2019
  ident: ref114
  article-title: Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning
– ident: ref124
  doi: 10.1007/s10994-013-5399-7
– ident: ref50
  doi: 10.1017/jfm.2016.615
– volume: 34
  year: 2015
  ident: ref42
  article-title: Data-driven fluid simulations using regression forests
  publication-title: ACM Trans Graph
– start-page: 1733
  year: 2018
  ident: ref66
  article-title: Learning to exploit stability for 3D scene parsing
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref102
  doi: 10.1016/j.ijar.2005.10.003
– ident: ref79
  doi: 10.24963/ijcai.2018/643
– ident: ref34
  doi: 10.3390/machines5010004
– start-page: 1002
  year: 2012
  ident: ref77
  article-title: Markov logic mixtures of gaussian processes: Towards machines reading regression data
  publication-title: Proc Artif Intell Statist
– ident: ref60
  doi: 10.1016/j.ijmachtools.2006.04.007
– start-page: 140
  year: 2018
  ident: ref78
  article-title: Learning pipelines with limited data and domain knowledge: A study in parsing physics problems
  publication-title: Neural Inf Process Syst
– ident: ref47
  doi: 10.1002/aic.690381003
– ident: ref122
  doi: 10.1186/1752-0509-4-121
– ident: ref105
  doi: 10.1109/VAST.2012.6400486
– ident: ref85
  doi: 10.18653/v1/P16-1228
– year: 2016
  ident: ref62
  article-title: A compositional object-based approach to learning physical dynamics
– ident: ref104
  doi: 10.1609/aaai.v32i1.11757
– ident: ref132
  doi: 10.1145/3386252
– ident: ref68
  doi: 10.1109/22.643839
– ident: ref51
  doi: 10.21468/SciPostPhys.5.3.028
– ident: ref55
  doi: 10.1109/BIBM.2018.8621379
– year: 2018
  ident: ref25
  article-title: Epistemiology
  publication-title: The Stanford Encyclopedia of Philosophy (Winter 2012 Edition)
– volume: 45
  start-page: 233
  year: 2007
  ident: ref95
  article-title: Bayesian network learning algorithms using structural restrictions
  publication-title: Int J Approx Reasoning
  doi: 10.1016/j.ijar.2006.06.009
– volume: 19
  year: 2008
  ident: ref27
  publication-title: The Blackwell Guide to the Philosophy of Science
– year: 2021
  ident: ref58
  article-title: Incorporating causal prior knowledge as path-constraints in Bayesian networks and maximal ancestral graphs
– ident: ref74
  doi: 10.1016/j.neucom.2018.02.029
– ident: ref151
  doi: 10.18653/v1/P18-1165
– year: 2016
  ident: ref71
  article-title: Exploiting cyclic symmetry in convolutional neural networks
– ident: ref123
  doi: 10.1007/s10472-009-9133-x
– ident: ref33
  doi: 10.1109/BigData.2018.8621955
– ident: ref141
  doi: 10.1002/0470018860.s00035
– start-page: 33
  year: 2018
  ident: ref40
  article-title: Informed machine learning through functional composition.
  publication-title: LWDA
– ident: ref2
  doi: 10.1109/MSP.2012.2205597
– ident: ref112
  doi: 10.1007/s10994-012-5296-5
– year: 2019
  ident: ref108
  article-title: Interpretations are useful: Penalizing explanations to align neural networks with prior knowledge
– start-page: 1
  year: 2012
  ident: ref91
  article-title: A short introduction to probabilistic soft logic
  publication-title: Proc NIPS Workshop Probabilistic Program Found Appl
– ident: ref80
  doi: 10.3115/1690219.1690287
– year: 2017
  ident: ref12
  article-title: Physics-guided neural networks (PGNN): An application in lake temperature modeling
– year: 2019
  ident: ref18
  article-title: Spigan: Privileged adversarial learning from simulation
  publication-title: Proc Int Conf Learn Representations
– year: 2018
  ident: ref119
  article-title: Bert: Pre-training of deep bidirectional transformers for language understanding
– ident: ref96
  doi: 10.1016/j.eswa.2016.02.050
– ident: ref111
  doi: 10.1109/MSP.2017.2693418
– ident: ref59
  doi: 10.1093/bioinformatics/btz199
– ident: ref130
  doi: 10.1017/CBO9781107706804
– year: 2020
  ident: ref8
  article-title: Toward trustworthy AI development: Mechanisms for supporting verifiable claims
– start-page: 1559
  year: 2018
  ident: ref16
  article-title: Hybrid knowledge routed modules for large-scale object detection
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref19
  doi: 10.1016/j.procir.2018.03.046
– year: 2020
  ident: ref142
  article-title: Neurosymbolic AI: The 3rd wave
– ident: ref5
  doi: 10.1038/s41586-018-0337-2
– year: 2018
  ident: ref41
  article-title: From deep to physics-informed learning of turbulence: Diagnostics
– ident: ref54
  doi: 10.1023/A:1008328630915
– ident: ref6
  doi: 10.1098/rsif.2017.0387
– year: 2020
  ident: ref39
  article-title: Compensating data shortages in manufacturing with monotonicity knowledge
– year: 2012
  ident: ref32
  publication-title: Learning From Data
– ident: ref127
  doi: 10.1007/978-3-540-70956-5_7
– ident: ref75
  doi: 10.1109/CVPR.2017.758
– start-page: 4509
  year: 2016
  ident: ref14
  article-title: Interaction networks for learning about objects, relations and physics
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref7
  doi: 10.1017/jfm.2016.803
– ident: ref69
  doi: 10.1023/A:1023283917997
– year: 2017
  ident: ref153
  article-title: Towards a rigorous science of interpretable machine learning
– ident: ref138
  doi: 10.1109/ICRA.2018.8460528
– ident: ref118
  doi: 10.1145/3191513
– start-page: 10203
  year: 2021
  ident: ref110
  article-title: Street-map based validation of semantic segmentation in autonomous driving
  publication-title: Proc Int Conf Pattern Recognit
– ident: ref21
  doi: 10.1016/j.artint.2015.08.011
– year: 2009
  ident: ref126
  article-title: Active learning literature survey
– year: 2003
  ident: ref31
  publication-title: Scientific Method in Practice
– start-page: 624
  year: 2003
  ident: ref101
  article-title: Learning with knowledge from multiple experts
  publication-title: Proc Int Conf Mach Learn
– ident: ref61
  doi: 10.1021/cm100795d
– ident: ref115
  doi: 10.1007/978-3-031-01574-8
– year: 2017
  ident: ref20
  article-title: Physics informed deep learning (part i): Data-driven solutions of nonlinear partial differential equations
– ident: ref46
  doi: 10.1016/j.jcp.2019.05.024
– ident: ref56
  doi: 10.1145/2783258.2783365
– year: 2011
  ident: ref136
  publication-title: Numerical Solution Of Partial Differential Equations in Science and Engineering
– ident: ref37
  doi: 10.1109/TNN.2008.2005188
– year: 2019
  ident: ref48
  article-title: Deep lagrangian networks: Using physics as model prior for deep learning
– ident: ref137
  doi: 10.1109/IROS.2017.8205961
– ident: ref90
  doi: 10.1007/s10994-006-5833-1
– ident: ref53
  doi: 10.1016/0004-3702(94)90105-8
– start-page: 1858
  year: 2018
  ident: ref81
  article-title: Symbolic graph reasoning meets convolutions
  publication-title: Proc Int Conf Neural Inf Process
– start-page: 537
  year: 2003
  ident: ref36
  article-title: Knowledge-based support vector machine classifiers
  publication-title: Proc 15th Int Conf Neural Inf Process Syst
– ident: ref30
  doi: 10.1017/S0140525X16001837
– year: 2020
  ident: ref149
  article-title: Learning from human feedback: Challenges for real-world reinforcement learning in NLP
– ident: ref45
  doi: 10.1109/72.712178
– year: 2013
  ident: ref121
  article-title: Efficient estimation of word representations in vector space
– start-page: 7178
  year: 2018
  ident: ref49
  article-title: End-to-end differentiable physics for learning and control
  publication-title: Proc Neural Inf Process Syst
– year: 2008
  ident: ref134
  publication-title: Support Vector Machines
– ident: ref38
  doi: 10.1007/978-3-030-30484-3_48
– year: 2015
  ident: ref144
  article-title: Hinge-loss Markov random fields and probabilistic soft logic
– year: 2017
  ident: ref99
  article-title: Beating atari with natural language guided reinforcement learning
– ident: ref86
  doi: 10.18653/v1/P19-1139
– year: 2003
  ident: ref129
  publication-title: Atmospheric Modeling Data Assimilation and Predictability
– ident: ref63
  doi: 10.1145/3097983.3098126
– ident: ref94
  doi: 10.18653/v1/D19-1005
– ident: ref52
  doi: 10.1103/PhysRevFluids.3.074602
– start-page: 4302
  year: 2017
  ident: ref103
  article-title: Deep reinforcement learning from human preferences
  publication-title: Proc Neural Inf Process Syst
– ident: ref97
  doi: 10.1109/TVCG.2013.212
– ident: ref26
  doi: 10.1002/9781405164863.ch3
– ident: ref76
  doi: 10.1109/5.726787
– volume: 2
  start-page: 62
  year: 1999
  ident: ref140
  article-title: Hybrid neural systems: From simple coupling to fully integrated neural networks
  publication-title: Neural Comput Surv
– year: 2016
  ident: ref87
  article-title: Counter-fitting word vectors to linguistic constraints
  doi: 10.18653/v1/N16-1018
– year: 0
  ident: ref11
  article-title: A semantic loss function for deep learning with symbolic knowledge
– ident: ref13
  doi: 10.1609/aaai.v31i1.10934
– ident: ref22
  doi: 10.1109/TKDE.2017.2720168
– ident: ref57
  doi: 10.1007/978-3-642-02906-6_16
– ident: ref133
  doi: 10.1017/CBO9780511618796
– year: 2011
  ident: ref29
  publication-title: Thinking Fast and Slow
– start-page: 5938
  year: 2017
  ident: ref131
  article-title: Self-supervised intrinsic image decomposition
  publication-title: Proc Neural Inf Process Syst
– ident: ref93
  doi: 10.24963/ijcai.2017/230
– ident: ref84
  doi: 10.18653/v1/D16-1173
– volume: 17
  year: 1996
  ident: ref28
  article-title: From data mining to knowledge discovery in databases
  publication-title: AI Mag
– year: 2018
  ident: ref24
  article-title: Relational inductive biases, deep learning, and graph networks
– start-page: 640
  year: 1998
  ident: ref72
  article-title: Prior knowledge in support vector kernels
  publication-title: Proc Conf Adv Neural Inf Process Syst
– ident: ref113
  doi: 10.3115/v1/P15-1012
– ident: ref147
  doi: 10.1561/9781680836233
– ident: ref10
  doi: 10.1109/ICMLA.2017.00-37
– volume: 12
  start-page: 34
  year: 1991
  ident: ref128
  article-title: Logical versus analogical or symbolic versus connectionist or neat versus scruffy
  publication-title: AI Mag
– ident: ref107
  doi: 10.1145/604045.604056
– year: 2018
  ident: ref43
  article-title: Physics-informed deep generative models
– ident: ref146
  doi: 10.1080/01621459.2017.1285773
– ident: ref120
  doi: 10.18653/v1/N19-1288
– ident: ref15
  doi: 10.1109/CVPR.2017.10
– ident: ref139
  doi: 10.1007/978-3-030-44584-3_43
– year: 2018
  ident: ref143
  article-title: Imposing category trees onto word-embeddings using a geometric construction
  publication-title: Proc Int Conf Learn Representations
– year: 2018
  ident: ref145
  article-title: Scalable structure learning for probabilistic soft logic
– ident: ref92
  doi: 10.18653/v1/P18-1004
– ident: ref117
  doi: 10.1145/219717.219748
– start-page: 501
  year: 2019
  ident: ref82
  article-title: Symmetry constrained machine learning
  publication-title: Proc SAI Intelligent Systems Conf
– ident: ref100
  doi: 10.1007/BF00994016
– year: 2019
  ident: ref150
  article-title: Challenges of real-world reinforcement learning
– ident: ref98
  doi: 10.1145/1597735.1597738
– start-page: 2242
  year: 2017
  ident: ref67
  article-title: Learning from simulated and unsupervised images through adversarial training
  publication-title: Proc IEEE Conf Comput Vis Pattern Recognit
– ident: ref152
  doi: 10.18653/v1/D18-1445
– ident: ref23
  doi: 10.1016/j.neucom.2007.04.010
– ident: ref106
  doi: 10.1016/j.jbi.2013.10.012
– start-page: 280
  year: 2007
  ident: ref83
  article-title: Guiding semi-supervision with constraint-driven learning
  publication-title: Assoc Comput Linguist
– ident: ref135
  doi: 10.1007/s102080010030
– volume: 20
  start-page: 1
  year: 2019
  ident: ref65
  article-title: Using simulation to improve sample-efficiency of Bayesian optimization for bipedal robots.
  publication-title: J Machine Learn Res
– ident: ref148
  doi: 10.1017/CBO9780511803161
SSID ssj0008781
Score 2.746319
Snippet Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 614
SubjectTerms expert knowledge
hybrid
informed
Knowledge representation
Machine learning
Mathematical model
neuro-symbolic
Pipelines
prior knowledge
survey
Systematics
Taxonomy
Training
Training data
Title Informed Machine Learning - A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems
URI https://ieeexplore.ieee.org/document/9429985
https://www.proquest.com/docview/2747610173
Volume 35
WOSCitedRecordID wos000895445500045&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 (IEL)
  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/eLvHCXMwlV1LSwMxEB5s8aAHH61ifZGDJ3Hb7WZ3kxyLDxS1FKzS25LmIQXZlW0r-u9NsmkVFMFbFiZhyZeZZCaZbwBOmIo0TlIWRFyFQcyECJgUcRBSwrH55NRx6T3dkX6fjkZssAJny1wYpZR7fKbatunu8mUh5jZU1mHWeNKkBjVC0ipXa2l1KXEFSY13YXwiHBN_g9kNWWd4e3FpPMGo2zYLmlVszF97kCuq8sMSu-3lavN_P7YFG_4YiXoV7tuwovIGbC5KNCCvsQ1Y_8Y32ARdJR8pie7dG0qFPL3qMwpQDw35u0txQDyX6GFevqkPVGh04xklrNignBQlul0E4tAknxVfg3j68x14vLocnl8HvtBCIDBOZ4GMGdHY5uQmESOcc4qxGHOtxiklWtsmp4mUWAueCDnWRuu7oY66ijAuqMS7UM-LXO0BihJlZjqShBqUJUuYwEIQ4-hxZk9WcQvCxdRnwrOQ22IYL5nzRkKWWbQyi1bm0WrB6bLLa0XB8Zdw08KzFPTItOBwgW_mlXSaWYc8tSYJ7__e6wDWbHX5KuJyCPVZOVdHsCreZpNpeezW3ycz-9hE
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD7oFNQH7-J0ah58Euu6pl2Sx-EFZXMMnOJbyXKRgbTSXdB_b5JmU1AE31JIQsmXc5KT5HwfwClTkcZJkwURV2EQMyECJkUchJRwbD45dVx6Tx3S7dLnZ9ZbgPN5LoxSyj0-Uxe26O7yZS4m9qiszqzzpMkiLFnlrKTM1pr7XUqcJKmJL0xUhGPi7zAbIav321fXJhaMGhdmSrOSj_lrFXKyKj98sVtgbjb-92ubsO43kqhVIr8FCyrbho2ZSAPyNrsNa98YB3dAl-lHSqJ794pSIU-w-oIC1EJ9_u6SHBDPJHqYFFP1gXKN7jynhK3WK4Z5gdqzozg0zMb5VyeeAH0XHm-u-5e3gZdaCATGzXEgY0Y0tlm5ScQI55xiLAZcq0GTEq1tkdNESqwFT4QcaGP3jVBHDUUYF1TiPahkeab2AUWJMiMdSUINzpIlTGAhiAn1OLN7q7gK4WzoU-F5yK0cxmvq4pGQpRat1KKVerSqcDZv8laScPxVecfCM6_okalCbYZv6s10lNqQvGmdEj74vdUJrNz27ztp567bPoRVqzVfnr_UoDIuJuoIlsV0PBwVx24ufgKk79uP
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=Informed+Machine+Learning+-+A+Taxonomy+and+Survey+of+Integrating+Prior+Knowledge+into+Learning+Systems&rft.jtitle=IEEE+transactions+on+knowledge+and+data+engineering&rft.au=von+Rueden%2C+Laura&rft.au=Mayer%2C+Sebastian&rft.au=Beckh%2C+Katharina&rft.au=Georgiev%2C+Bogdan&rft.date=2023-01-01&rft.issn=1041-4347&rft.eissn=1558-2191&rft.spage=1&rft.epage=1&rft_id=info:doi/10.1109%2FTKDE.2021.3079836&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TKDE_2021_3079836
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