Hypergraph convolution and hypergraph attention

•Hypergraph convolution defines a basic convolutional operator in a hypergraph. It enables an efficient information propagation between vertices by fully exploiting the high order relationship and local clustering structure therein. We mathematically prove that graph convolution is a special case of...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Pattern recognition Ročník 110; s. 107637
Hlavní autori: Bai, Song, Zhang, Feihu, Torr, Philip H.S.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.02.2021
Predmet:
ISSN:0031-3203, 1873-5142
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract •Hypergraph convolution defines a basic convolutional operator in a hypergraph. It enables an efficient information propagation between vertices by fully exploiting the high order relationship and local clustering structure therein. We mathematically prove that graph convolution is a special case of hypergraph convolution when the non pairwise relationship degenerates to a pairwise one.•Apart from hypergraph convolution where the underlying structure used for propagation is pre defined, hypergraph attention further exerts an attention mechanism to learn a dynamic connection of hyperedges. Then, the information propagation and gathering is done in task relevant parts of the graph, thereby generating more discriminative node embeddings.•Both hypergraph convolution and hypergraph attention are end to end trainable, and can be inserted into most variants of graph neural networks as long as non pairwise relationships are observed. Extensive experimental results on benchmark datasets demonstrate the efficacy of the proposed methods for semi supervised node classification. Recently, graph neural networks have attracted great attention and achieved prominent performance in various research fields. Most of those algorithms have assumed pairwise relationships of objects of interest. However, in many real applications, the relationships between objects are in higher-order, beyond a pairwise formulation. To efficiently learn deep embeddings on the high-order graph-structured data, we introduce two end-to-end trainable operators to the family of graph neural networks, i.e., hypergraph convolution and hypergraph attention. Whilst hypergraph convolution defines the basic formulation of performing convolution on a hypergraph, hypergraph attention further enhances the capacity of representation learning by leveraging an attention module. With the two operators, a graph neural network is readily extended to a more flexible model and applied to diverse applications where non-pairwise relationships are observed. Extensive experimental results with semi-supervised node classification demonstrate the effectiveness of hypergraph convolution and hypergraph attention.
AbstractList •Hypergraph convolution defines a basic convolutional operator in a hypergraph. It enables an efficient information propagation between vertices by fully exploiting the high order relationship and local clustering structure therein. We mathematically prove that graph convolution is a special case of hypergraph convolution when the non pairwise relationship degenerates to a pairwise one.•Apart from hypergraph convolution where the underlying structure used for propagation is pre defined, hypergraph attention further exerts an attention mechanism to learn a dynamic connection of hyperedges. Then, the information propagation and gathering is done in task relevant parts of the graph, thereby generating more discriminative node embeddings.•Both hypergraph convolution and hypergraph attention are end to end trainable, and can be inserted into most variants of graph neural networks as long as non pairwise relationships are observed. Extensive experimental results on benchmark datasets demonstrate the efficacy of the proposed methods for semi supervised node classification. Recently, graph neural networks have attracted great attention and achieved prominent performance in various research fields. Most of those algorithms have assumed pairwise relationships of objects of interest. However, in many real applications, the relationships between objects are in higher-order, beyond a pairwise formulation. To efficiently learn deep embeddings on the high-order graph-structured data, we introduce two end-to-end trainable operators to the family of graph neural networks, i.e., hypergraph convolution and hypergraph attention. Whilst hypergraph convolution defines the basic formulation of performing convolution on a hypergraph, hypergraph attention further enhances the capacity of representation learning by leveraging an attention module. With the two operators, a graph neural network is readily extended to a more flexible model and applied to diverse applications where non-pairwise relationships are observed. Extensive experimental results with semi-supervised node classification demonstrate the effectiveness of hypergraph convolution and hypergraph attention.
ArticleNumber 107637
Author Torr, Philip H.S.
Bai, Song
Zhang, Feihu
Author_xml – sequence: 1
  givenname: Song
  orcidid: 0000-0002-2570-9118
  surname: Bai
  fullname: Bai, Song
  email: songbai.site@gmail.com
– sequence: 2
  givenname: Feihu
  surname: Zhang
  fullname: Zhang, Feihu
  email: feihu.zhang@eng.ox.ac.uk
– sequence: 3
  givenname: Philip H.S.
  surname: Torr
  fullname: Torr, Philip H.S.
  email: philip.torr@eng.ox.ac.uk
BookMark eNqFj8FKAzEQhoNUsK2-gYe-wG5nkt3s6kGQoq1Q8KLnkCbTNqUmSzYW-vbusoLgQU8zzM_3M9-EjXzwxNgtQo6Acn7IG51M2OUceH-qpKgu2BjrSmQlFnzExgACM8FBXLFJ2x4AsOqCMZuvzg3FXdTNfmaCP4XjZ3LBz7S3s_1PpFMi3wfX7HKrjy3dfM8pe39-elussvXr8mXxuM6MAJky3EqoSdaASESCaCNq3FBVkLUIvNtkSfyOoLJQClkWuuCihgKl5YZKEFN2P_SaGNo20lYZl3T_QYraHRWC6tXVQQ3qqldXg3oHF7_gJroPHc__YQ8DRp3YyVFUrXHkDVkXySRlg_u74At3lnb1
CitedBy_id crossref_primary_10_26599_BDMA_2024_9020091
crossref_primary_10_1016_j_jclepro_2023_138880
crossref_primary_10_1109_LGRS_2024_3379232
crossref_primary_10_1109_TAI_2023_3337052
crossref_primary_10_1109_TITS_2022_3168879
crossref_primary_10_1007_s10115_023_02058_3
crossref_primary_10_1109_TSC_2023_3237638
crossref_primary_10_1016_j_knosys_2023_110810
crossref_primary_10_1016_j_measurement_2024_114586
crossref_primary_10_1109_TNSE_2025_3547349
crossref_primary_10_1371_journal_pcbi_1013012
crossref_primary_10_1016_j_aei_2024_102518
crossref_primary_10_1016_j_eswa_2023_119875
crossref_primary_10_3390_s24237655
crossref_primary_10_1109_TPAMI_2024_3353199
crossref_primary_10_1016_j_ipm_2025_104180
crossref_primary_10_1109_TCSS_2024_3408214
crossref_primary_10_1109_TFUZZ_2025_3573914
crossref_primary_10_1109_TMC_2025_3532992
crossref_primary_10_1109_JSTARS_2024_3522318
crossref_primary_10_1007_s10844_024_00887_4
crossref_primary_10_1016_j_ymssp_2025_112987
crossref_primary_10_1016_j_asoc_2025_112855
crossref_primary_10_1109_JBHI_2024_3384238
crossref_primary_10_1007_s10115_022_01786_2
crossref_primary_10_1109_TIM_2024_3403176
crossref_primary_10_1016_j_media_2023_102828
crossref_primary_10_3390_app15158324
crossref_primary_10_1016_j_eswa_2024_125106
crossref_primary_10_1109_TCST_2024_3496439
crossref_primary_10_3390_math12182887
crossref_primary_10_1109_JSTARS_2024_3483560
crossref_primary_10_7717_peerj_13163
crossref_primary_10_1016_j_cmpb_2024_108099
crossref_primary_10_1109_TNNLS_2024_3371382
crossref_primary_10_1109_TPAMI_2023_3332768
crossref_primary_10_1016_j_neucom_2022_06_070
crossref_primary_10_1109_TKDE_2025_3581419
crossref_primary_10_1109_TSG_2024_3524629
crossref_primary_10_1145_3652865
crossref_primary_10_1109_TBDATA_2024_3442549
crossref_primary_10_1016_j_cag_2023_07_011
crossref_primary_10_1007_s10489_024_05491_1
crossref_primary_10_1007_s11227_024_06003_1
crossref_primary_10_1016_j_ab_2024_115628
crossref_primary_10_1016_j_knosys_2021_107528
crossref_primary_10_1016_j_neucom_2025_130600
crossref_primary_10_1016_j_knosys_2024_112177
crossref_primary_10_1145_3665931
crossref_primary_10_1109_ACCESS_2024_3398367
crossref_primary_10_1109_TCE_2024_3365066
crossref_primary_10_1016_j_neuroimage_2025_121422
crossref_primary_10_1016_j_jocs_2022_101905
crossref_primary_10_1016_j_patcog_2023_110115
crossref_primary_10_3233_IDA_216007
crossref_primary_10_1109_TGRS_2025_3534288
crossref_primary_10_1145_3610535
crossref_primary_10_1016_j_neucom_2024_127989
crossref_primary_10_1109_TBDATA_2023_3275374
crossref_primary_10_1109_TIFS_2023_3254449
crossref_primary_10_1109_TIM_2022_3212532
crossref_primary_10_3390_diagnostics12112632
crossref_primary_10_1109_TMI_2022_3204538
crossref_primary_10_1109_TNNLS_2025_3553385
crossref_primary_10_1016_j_scs_2024_106016
crossref_primary_10_1038_s42256_023_00785_4
crossref_primary_10_1016_j_compbiomed_2025_110446
crossref_primary_10_1016_j_neunet_2023_10_050
crossref_primary_10_1109_TIFS_2024_3518068
crossref_primary_10_1016_j_neunet_2023_07_006
crossref_primary_10_1007_s13042_024_02124_4
crossref_primary_10_1145_3609468_3609472
crossref_primary_10_1016_j_knosys_2024_112825
crossref_primary_10_1016_j_ins_2023_03_078
crossref_primary_10_1109_TGRS_2024_3486684
crossref_primary_10_1109_JBHI_2024_3355111
crossref_primary_10_1109_TCYB_2025_3558941
crossref_primary_10_1016_j_asoc_2025_112721
crossref_primary_10_1007_s10791_024_09439_4
crossref_primary_10_1016_j_neucom_2025_129721
crossref_primary_10_1007_s13042_025_02659_0
crossref_primary_10_1016_j_neucom_2024_129264
crossref_primary_10_1109_TSIPN_2023_3345142
crossref_primary_10_1109_TCSS_2024_3419008
crossref_primary_10_1007_s10489_025_06808_4
crossref_primary_10_1088_2632_072X_ad0e23
crossref_primary_10_1007_s40747_022_00964_7
crossref_primary_10_1016_j_eswa_2024_123412
crossref_primary_10_1109_TMM_2025_3542958
crossref_primary_10_1109_TPAMI_2021_3078053
crossref_primary_10_1007_s41060_025_00797_w
crossref_primary_10_1109_COMST_2023_3319492
crossref_primary_10_1109_ACCESS_2024_3461782
crossref_primary_10_1109_ACCESS_2022_3219873
crossref_primary_10_1145_3733234
crossref_primary_10_1007_s10489_024_06111_8
crossref_primary_10_1016_j_jmsy_2024_06_011
crossref_primary_10_1016_j_patcog_2024_110292
crossref_primary_10_1007_s10618_024_01021_2
crossref_primary_10_1016_j_chaos_2024_114864
crossref_primary_10_1016_j_eswa_2025_129116
crossref_primary_10_1016_j_ipm_2025_104268
crossref_primary_10_1007_s00371_022_02499_x
crossref_primary_10_3390_app14083526
crossref_primary_10_1016_j_patcog_2025_111775
crossref_primary_10_1145_3494567
crossref_primary_10_1016_j_isatra_2025_04_017
crossref_primary_10_1145_3663670
crossref_primary_10_1109_TNSM_2023_3257993
crossref_primary_10_1109_ACCESS_2022_3231889
crossref_primary_10_1007_s10618_023_00952_6
crossref_primary_10_1016_j_asoc_2024_112400
crossref_primary_10_1109_TCAD_2024_3436013
crossref_primary_10_1117_1_JEI_33_1_013022
crossref_primary_10_1016_j_asoc_2024_112524
crossref_primary_10_1109_TNSE_2022_3217185
crossref_primary_10_1007_s10994_024_06566_3
crossref_primary_10_1051_e3sconf_202022401025
crossref_primary_10_1109_JSTARS_2021_3136599
crossref_primary_10_1145_3610297
crossref_primary_10_1093_bib_bbae067
crossref_primary_10_1109_JSTARS_2023_3252670
crossref_primary_10_1016_j_ress_2024_110143
crossref_primary_10_1016_j_physd_2023_133834
crossref_primary_10_3390_act14050242
crossref_primary_10_1093_bib_bbae500
crossref_primary_10_1016_j_neucom_2024_128639
crossref_primary_10_1145_3544977
crossref_primary_10_1109_ACCESS_2024_3361680
crossref_primary_10_1016_j_trc_2025_105257
crossref_primary_10_1016_j_neunet_2025_107729
crossref_primary_10_1109_TGRS_2023_3345159
crossref_primary_10_1109_TPAMI_2023_3323624
crossref_primary_10_1016_j_neunet_2024_106432
crossref_primary_10_3390_math10203905
crossref_primary_10_1016_j_eswa_2025_129497
crossref_primary_10_1016_j_knosys_2023_111254
crossref_primary_10_1016_j_jer_2024_08_006
crossref_primary_10_1016_j_infsof_2023_107219
crossref_primary_10_1109_TGRS_2021_3123423
crossref_primary_10_1016_j_patcog_2023_109677
crossref_primary_10_1093_bib_bbad522
crossref_primary_10_1016_j_cmpb_2025_108971
crossref_primary_10_3390_ijgi13090334
crossref_primary_10_1016_j_bspc_2025_108049
crossref_primary_10_1038_s41598_024_66349_7
crossref_primary_10_1016_j_knosys_2025_114435
crossref_primary_10_1007_s10707_024_00527_7
crossref_primary_10_1016_j_optlastec_2024_112199
crossref_primary_10_3390_info16040267
crossref_primary_10_3390_electronics13224435
crossref_primary_10_1016_j_asoc_2024_111899
crossref_primary_10_1016_j_neucom_2025_131312
crossref_primary_10_3390_sym16111436
crossref_primary_10_1016_j_engappai_2022_105174
crossref_primary_10_1109_TIM_2022_3219475
crossref_primary_10_1155_2021_7716214
crossref_primary_10_1109_TVT_2024_3365213
crossref_primary_10_1007_s10489_024_05939_4
crossref_primary_10_1016_j_ipm_2023_103376
crossref_primary_10_1016_j_knosys_2024_111903
crossref_primary_10_1093_bib_bbad391
crossref_primary_10_1016_j_neucom_2021_08_006
crossref_primary_10_1016_j_patcog_2023_109543
crossref_primary_10_1016_j_neunet_2024_106929
crossref_primary_10_1109_TPAMI_2023_3331389
crossref_primary_10_1016_j_neunet_2024_106807
crossref_primary_10_1109_TKDE_2025_3568709
crossref_primary_10_1016_j_neunet_2022_08_028
crossref_primary_10_1109_TBDATA_2025_3527216
crossref_primary_10_3390_app13010523
crossref_primary_10_1109_JSEN_2021_3136622
crossref_primary_10_1002_aoc_70188
crossref_primary_10_3390_make7020040
crossref_primary_10_1007_s10994_021_06090_8
crossref_primary_10_1007_s11263_024_02298_y
crossref_primary_10_1093_bib_bbaf321
crossref_primary_10_1007_s41468_024_00172_x
crossref_primary_10_1109_TPAMI_2022_3178156
crossref_primary_10_1007_s40305_025_00630_y
crossref_primary_10_1093_bioinformatics_btaf379
crossref_primary_10_1109_TKDE_2025_3565306
crossref_primary_10_1007_s00521_023_08935_w
crossref_primary_10_1109_TNNLS_2025_3542176
crossref_primary_10_1109_TBDATA_2025_3533908
crossref_primary_10_1063_5_0193557
crossref_primary_10_1016_j_patcog_2025_111614
crossref_primary_10_1109_TSC_2023_3334241
crossref_primary_10_1016_j_dss_2025_114527
crossref_primary_10_1016_j_neucom_2023_126992
crossref_primary_10_1109_TKDE_2024_3380643
crossref_primary_10_1016_j_patcog_2022_108869
crossref_primary_10_1177_30504554251347451
crossref_primary_10_1145_3627816
crossref_primary_10_1016_j_patcog_2024_110260
crossref_primary_10_1177_03611981241295706
crossref_primary_10_1038_s42004_022_00790_5
crossref_primary_10_1080_17538947_2024_2413890
crossref_primary_10_1007_s42979_024_03644_0
crossref_primary_10_1093_bfgp_elaf009
crossref_primary_10_1109_TMM_2024_3521738
crossref_primary_10_1016_j_energy_2025_135170
crossref_primary_10_1016_j_knosys_2025_114005
crossref_primary_10_1109_JSEN_2023_3319537
crossref_primary_10_1007_s11192_024_05066_4
crossref_primary_10_1109_LSP_2024_3419424
crossref_primary_10_1109_TSC_2024_3489417
crossref_primary_10_1016_j_eswa_2025_126587
crossref_primary_10_1016_j_ipm_2024_103877
crossref_primary_10_1109_TNSE_2023_3243058
crossref_primary_10_1080_17538947_2024_2303354
crossref_primary_10_1016_j_patcog_2025_111995
crossref_primary_10_1016_j_patcog_2023_109995
crossref_primary_10_1109_TII_2024_3393137
crossref_primary_10_1109_TNNLS_2023_3263676
crossref_primary_10_1145_3631444
crossref_primary_10_3390_electronics12183952
crossref_primary_10_1007_s10479_021_03953_0
crossref_primary_10_1109_TMM_2021_3120544
crossref_primary_10_1186_s12864_021_07864_z
crossref_primary_10_1109_TCOMM_2024_3511952
crossref_primary_10_1145_3604932
crossref_primary_10_1016_j_cities_2025_106300
crossref_primary_10_1016_j_cmpb_2024_108237
crossref_primary_10_1109_TSG_2024_3386609
crossref_primary_10_1155_2024_5791802
crossref_primary_10_1007_s10489_025_06348_x
crossref_primary_10_1016_j_ins_2024_121165
crossref_primary_10_1109_TGRS_2025_3598612
crossref_primary_10_1371_journal_pcbi_1011597
crossref_primary_10_3390_rs15030694
crossref_primary_10_1016_j_ins_2022_10_006
crossref_primary_10_1016_j_patcog_2023_109759
crossref_primary_10_1111_tgis_13276
crossref_primary_10_1016_j_knosys_2025_114352
crossref_primary_10_1016_j_patcog_2023_109519
crossref_primary_10_1007_s00371_024_03269_7
crossref_primary_10_1016_j_jksuci_2023_101852
crossref_primary_10_1016_j_physa_2025_130725
crossref_primary_10_1109_TAI_2024_3450658
crossref_primary_10_1080_2150704X_2024_2320177
crossref_primary_10_1007_s11042_024_18111_4
crossref_primary_10_1016_j_knosys_2024_112119
crossref_primary_10_1109_TBDATA_2024_3453757
crossref_primary_10_1007_s10489_023_05035_z
crossref_primary_10_1016_j_eswa_2023_123091
crossref_primary_10_1093_llc_fqad071
crossref_primary_10_3390_technologies13060257
crossref_primary_10_1109_LGRS_2025_3583697
crossref_primary_10_1007_s12530_024_09650_0
crossref_primary_10_1016_j_fnutr_2025_100020
crossref_primary_10_1016_j_cosrev_2024_100722
crossref_primary_10_3390_app14093832
crossref_primary_10_1016_j_patcog_2022_108539
crossref_primary_10_1186_s40537_025_01170_1
crossref_primary_10_3390_axioms13060387
crossref_primary_10_1007_s12204_024_2699_y
crossref_primary_10_1145_3633518
crossref_primary_10_3390_e25010089
crossref_primary_10_1016_j_inffus_2023_102149
crossref_primary_10_1016_j_patcog_2023_109867
crossref_primary_10_1007_s10115_024_02259_4
crossref_primary_10_1007_s10462_025_11199_6
crossref_primary_10_1109_TPAMI_2024_3434483
crossref_primary_10_1016_j_eswa_2023_121230
crossref_primary_10_1080_01431161_2024_2343133
crossref_primary_10_1007_s11042_023_16440_4
crossref_primary_10_1016_j_eswa_2024_123369
crossref_primary_10_1109_TPAMI_2022_3182052
crossref_primary_10_3389_frai_2024_1408843
crossref_primary_10_1109_TMM_2022_3183388
crossref_primary_10_1109_TMM_2024_3373255
crossref_primary_10_3390_a13120318
crossref_primary_10_3390_s24196391
crossref_primary_10_1016_j_eswa_2023_121805
crossref_primary_10_1109_ACCESS_2023_3347608
crossref_primary_10_3390_electronics12224703
crossref_primary_10_1109_TNNLS_2024_3502769
crossref_primary_10_1177_00222437251349798
crossref_primary_10_1364_OE_564525
crossref_primary_10_1007_s00530_024_01355_3
crossref_primary_10_1016_j_ipm_2022_103106
crossref_primary_10_1109_TPAMI_2020_3032542
crossref_primary_10_1016_j_engappai_2025_110799
crossref_primary_10_1109_TKDE_2025_3539769
crossref_primary_10_1145_3613964
crossref_primary_10_3390_app11093867
crossref_primary_10_1109_TGRS_2025_3542422
crossref_primary_10_1016_j_inffus_2025_103149
crossref_primary_10_1109_TNNLS_2023_3261860
crossref_primary_10_1016_j_engappai_2025_110441
crossref_primary_10_1186_s13677_023_00556_x
crossref_primary_10_1007_s11633_022_1397_1
crossref_primary_10_1016_j_knosys_2025_114283
crossref_primary_10_1145_3605776
crossref_primary_10_1109_TMI_2023_3253760
crossref_primary_10_1109_ACCESS_2025_3592104
crossref_primary_10_1109_TPAMI_2025_3585179
crossref_primary_10_1016_j_knosys_2024_112107
crossref_primary_10_1038_s41598_024_70565_6
crossref_primary_10_1007_s11571_022_09890_3
crossref_primary_10_3390_make7030094
crossref_primary_10_1016_j_bspc_2025_108568
crossref_primary_10_1016_j_aei_2024_102940
crossref_primary_10_3390_math13060998
crossref_primary_10_1145_3544105
crossref_primary_10_1145_3697841
crossref_primary_10_1016_j_ipm_2024_103847
crossref_primary_10_1016_j_neucom_2025_130863
crossref_primary_10_1109_ACCESS_2024_3491213
crossref_primary_10_1016_j_ipm_2022_102950
crossref_primary_10_1007_s11227_022_04882_w
Cites_doi 10.1109/MSP.2012.2205597
10.1109/TPAMI.2012.60
10.1080/0308108031000084374
10.1109/TNN.2008.2005605
10.1016/j.patcog.2014.09.002
10.1145/3363574
10.1109/43.784130
10.1016/j.patcog.2019.107040
10.1016/j.patcog.2008.12.029
10.1016/j.patcog.2013.01.004
10.1016/0012-365X(93)90322-K
10.1109/MSP.2017.2693418
10.24963/ijcai.2020/303
10.1016/j.patcog.2017.05.009
ContentType Journal Article
Copyright 2020 Elsevier Ltd
Copyright_xml – notice: 2020 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.patcog.2020.107637
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1873-5142
ExternalDocumentID 10_1016_j_patcog_2020_107637
S0031320320304404
GroupedDBID --K
--M
-D8
-DT
-~X
.DC
.~1
0R~
123
1B1
1RT
1~.
1~5
29O
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABEFU
ABFNM
ABFRF
ABHFT
ABJNI
ABMAC
ABTAH
ABXDB
ABYKQ
ACBEA
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADMXK
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FD6
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
G8K
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
KOM
KZ1
LG9
LMP
LY1
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
RNS
ROL
RPZ
SBC
SDF
SDG
SDP
SDS
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
TN5
UNMZH
VOH
WUQ
XJE
XPP
ZMT
ZY4
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c306t-1f608e68011eee3eeb381be74edd102be765e29e07d053654a42380416d2ce503
ISICitedReferencesCount 473
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000585303400005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0031-3203
IngestDate Tue Nov 18 22:43:09 EST 2025
Sat Nov 29 07:27:55 EST 2025
Fri Feb 23 02:46:15 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Graph learning
Hypergraph learning
Graph neural networks
Semi-supervised learning
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-1f608e68011eee3eeb381be74edd102be765e29e07d053654a42380416d2ce503
ORCID 0000-0002-2570-9118
ParticipantIDs crossref_citationtrail_10_1016_j_patcog_2020_107637
crossref_primary_10_1016_j_patcog_2020_107637
elsevier_sciencedirect_doi_10_1016_j_patcog_2020_107637
PublicationCentury 2000
PublicationDate February 2021
2021-02-00
PublicationDateYYYYMMDD 2021-02-01
PublicationDate_xml – month: 02
  year: 2021
  text: February 2021
PublicationDecade 2020
PublicationTitle Pattern recognition
PublicationYear 2021
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Chen, Zhu, Song (bib0033) 2018
Duvenaud, Maclaurin, Iparraguirre, Bombarell, Hirzel, Aspuru-Guzik, Adams (bib0023) 2015
Xu, Li, Tian, Sonobe, Kawarabayashi, Jegelka (bib0030) 2018
Lu, Getoor (bib0064) 2003
Gilmer, Schoenholz, Riley, Vinyals, Dahl (bib0027) 2017
You, Ying, Ren, Hamilton, Leskovec (bib0035) 2018
Ying, He, Chen, Eksombatchai, Hamilton, Leskovec (bib0008) 2018
P.W. Battaglia, J.B. Hamrick, V. Bapst, A. Sanchez-Gonzalez, V. Zambaldi, M. Malinowski, A. Tacchetti, D. Raposo, A. Santoro, R. Faulkner, et al., Relational inductive biases, deep learning, and graph networks, arXiv
Sen, Namata, Bilgic, Getoor, Galligher, Eliassi-Rad (bib0053) 2008; 29
Zhuang, Ma (bib0026) 2018
Chen, Ma, Xiao (bib0032) 2018
Hinton, Deng, Yu, Dahl, Mohamed, Jaitly, Senior, Vanhoucke, Nguyen, Sainath (bib0003) 2012; 29
Li, Chen, Koltun (bib0075) 2018
Zien, Schlag, Chan (bib0045) 1999; 18
Dai, Li, Tian, Huang, Wang, Zhu, Song (bib0037) 2018
R.K. Srivastava, K. Greff, J. Schmidhuber, Highway networks, arXiv
Bahdanau, Cho, Bengio (bib0004) 2015
Pedronette, Valem, Almeida, Torres (bib0013) 2019; 28
M. Henaff, J. Bruna, Y. LeCun, Deep convolutional networks on graph-structured data, arXiv
Li, Tarlow, Brockschmidt, Zemel (bib0028) 2016
Li, Milenkovic (bib0044) 2017
Maas, Hannun, Ng (bib0050) 2013
Bronstein, Bruna, LeCun, Szlam, Vandergheynst (bib0009) 2017; 34
Schlichtkrull, Kipf, Bloem, van den Berg, Titov, Welling (bib0066) 2018
Yu, Tao, Wang (bib0012) 2012; 21
(2015).
Pham, Tran, Phung, Venkatesh (bib0029) 2017
Perozzi, Al-Rfou, Skiena (bib0063) 2014
B. Fatemi, P. Taslakian, D. Vazquez, D. Poole, Knowledge hypergraphs: prediction beyond binary relations, arXiv
Jin, Yu, You, Zeng, Li, Yu (bib0074) 2015; 48
Bolla (bib0046) 1993; 117
He, Zhang, Ren, Sun (bib0002) 2016
C. Berge, Graphs and hypergraphs (1973).
Velickovic, Cucurull, Casanova, Romero, Lio, Bengio (bib0031) 2018
Zhang, Hu, Tang, Chan (bib0011) 2017
(2019).
Xie, Girshick, Dollár, Tu, He (bib0056) 2017
Scarselli, Gori, Tsoi, Hagenbuchner, Monfardini (bib0005) 2009; 20
Ying, You, Morris, Ren, Hamilton, Leskovec (bib0034) 2018
Weston, Ratle, Mobahi, Collobert (bib0061) 2012
Zhou, Huang, Schölkopf (bib0048) 2007
Yang, Cohen, Salakhutdinov (bib0058) 2016
Krizhevsky, Sutskever, Hinton (bib0001) 2012
Niepert, Ahmed, Kutzkov (bib0024) 2016
You, Liu, Ying, Pande, Leskovec (bib0067) 2018
Defferrard, Bresson, Vandergheynst (bib0021) 2016
Feng, You, Zhang, Ji, Gao (bib0049) 2019
Zhou, Bai, Liu, Zhou, Hancock (bib0070) 2020; 98
Rodriguez (bib0047) 2003; 51
Simonovsky, Komodakis (bib0065) 2017
Zhu, Ghahramani, Lafferty (bib0062) 2003
Monti, Boscaini, Masci, Rodola, Svoboda, Bronstein (bib0040) 2017
J. Zhou, G. Cui, Z. Zhang, C. Yang, Z. Liu, M. Sun, Graph neural networks: a review of methods and applications, arXiv
Kingma, Ba (bib0059) 2015
Pedronette, Gonçalves, Guilherme (bib0017) 2018; 75
Huang, Liu, Zhang, Metaxas (bib0052) 2010
Xiao, Hancock, Wilson (bib0068) 2009; 42
Zhang, Cui, Zhu (bib0014) 2020
Boscaini, Masci, Rodolà, Bronstein (bib0042) 2016
Agarwal, Branson, Belongie (bib0010) 2006
Xiao, Yi-Zhe, Hall (bib0069) 2011; 115
Hamilton, Ying, Leskovec (bib0006) 2017
Narasimhan, Lazebnik, Schwing (bib0071) 2018
Liu, Allamanis, Brockschmidt, Gaunt (bib0072) 2018
Kipf, Welling (bib0022) 2017
Belkin, Niyogi, Sindhwani (bib0060) 2006; 7
Atwood, Towsley (bib0025) 2016
Lee, Rossi, Kim, Ahmed, Koh (bib0039) 2019; 13
Rahimi, Cohn, Baldwin (bib0055) 2018
Yang, Prasad, Latecki (bib0016) 2012; 35
Wang, Ye, Gupta (bib0007) 2018
Bruna, Zaremba, Szlam, LeCun (bib0019) 2014
Bojchevski, Shchur, Zügner, Günnemann (bib0036) 2018
Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (bib0057) 2017
(2018).
Masci, Boscaini, Bronstein, Vandergheynst (bib0041) 2015
Pedronette, Torres (bib0018) 2013; 46
Clevert, Unterthiner, Hochreiter (bib0051) 2016
10.1016/j.patcog.2020.107637_bib0038
Feng (10.1016/j.patcog.2020.107637_bib0049) 2019
Liu (10.1016/j.patcog.2020.107637_bib0072) 2018
10.1016/j.patcog.2020.107637_bib0073
Kipf (10.1016/j.patcog.2020.107637_bib0022) 2017
Vaswani (10.1016/j.patcog.2020.107637_bib0057) 2017
Bahdanau (10.1016/j.patcog.2020.107637_bib0004) 2015
Hamilton (10.1016/j.patcog.2020.107637_bib0006) 2017
Bojchevski (10.1016/j.patcog.2020.107637_bib0036) 2018
Zhu (10.1016/j.patcog.2020.107637_bib0062) 2003
Li (10.1016/j.patcog.2020.107637_bib0075) 2018
Bolla (10.1016/j.patcog.2020.107637_bib0046) 1993; 117
Krizhevsky (10.1016/j.patcog.2020.107637_bib0001) 2012
You (10.1016/j.patcog.2020.107637_bib0035) 2018
Sen (10.1016/j.patcog.2020.107637_bib0053) 2008; 29
Zhang (10.1016/j.patcog.2020.107637_bib0014) 2020
Schlichtkrull (10.1016/j.patcog.2020.107637_bib0066) 2018
Weston (10.1016/j.patcog.2020.107637_bib0061) 2012
Velickovic (10.1016/j.patcog.2020.107637_bib0031) 2018
10.1016/j.patcog.2020.107637_bib0043
Ying (10.1016/j.patcog.2020.107637_bib0034) 2018
He (10.1016/j.patcog.2020.107637_bib0002) 2016
Kingma (10.1016/j.patcog.2020.107637_bib0059) 2015
Boscaini (10.1016/j.patcog.2020.107637_bib0042) 2016
Zhou (10.1016/j.patcog.2020.107637_bib0048) 2007
Zhuang (10.1016/j.patcog.2020.107637_bib0026) 2018
Duvenaud (10.1016/j.patcog.2020.107637_bib0023) 2015
Atwood (10.1016/j.patcog.2020.107637_bib0025) 2016
Pham (10.1016/j.patcog.2020.107637_bib0029) 2017
Xiao (10.1016/j.patcog.2020.107637_bib0069) 2011; 115
Wang (10.1016/j.patcog.2020.107637_bib0007) 2018
Simonovsky (10.1016/j.patcog.2020.107637_bib0065) 2017
Pedronette (10.1016/j.patcog.2020.107637_bib0013) 2019; 28
Perozzi (10.1016/j.patcog.2020.107637_bib0063) 2014
Scarselli (10.1016/j.patcog.2020.107637_bib0005) 2009; 20
Rahimi (10.1016/j.patcog.2020.107637_bib0055) 2018
Xu (10.1016/j.patcog.2020.107637_bib0030) 2018
Dai (10.1016/j.patcog.2020.107637_bib0037) 2018
Xiao (10.1016/j.patcog.2020.107637_bib0068) 2009; 42
Chen (10.1016/j.patcog.2020.107637_bib0032) 2018
Hinton (10.1016/j.patcog.2020.107637_bib0003) 2012; 29
Zhou (10.1016/j.patcog.2020.107637_bib0070) 2020; 98
Jin (10.1016/j.patcog.2020.107637_bib0074) 2015; 48
Bruna (10.1016/j.patcog.2020.107637_bib0019) 2014
Zhang (10.1016/j.patcog.2020.107637_bib0011) 2017
10.1016/j.patcog.2020.107637_bib0015
Belkin (10.1016/j.patcog.2020.107637_bib0060) 2006; 7
Maas (10.1016/j.patcog.2020.107637_bib0050) 2013
10.1016/j.patcog.2020.107637_bib0054
Lee (10.1016/j.patcog.2020.107637_bib0039) 2019; 13
Xie (10.1016/j.patcog.2020.107637_bib0056) 2017
Ying (10.1016/j.patcog.2020.107637_bib0008) 2018
You (10.1016/j.patcog.2020.107637_bib0067) 2018
Huang (10.1016/j.patcog.2020.107637_bib0052) 2010
Agarwal (10.1016/j.patcog.2020.107637_bib0010) 2006
Clevert (10.1016/j.patcog.2020.107637_bib0051) 2016
Bronstein (10.1016/j.patcog.2020.107637_bib0009) 2017; 34
Pedronette (10.1016/j.patcog.2020.107637_bib0018) 2013; 46
Gilmer (10.1016/j.patcog.2020.107637_bib0027) 2017
Yu (10.1016/j.patcog.2020.107637_bib0012) 2012; 21
Chen (10.1016/j.patcog.2020.107637_bib0033) 2018
Yang (10.1016/j.patcog.2020.107637_bib0016) 2012; 35
Defferrard (10.1016/j.patcog.2020.107637_bib0021) 2016
Li (10.1016/j.patcog.2020.107637_bib0028) 2016
Narasimhan (10.1016/j.patcog.2020.107637_bib0071) 2018
10.1016/j.patcog.2020.107637_bib0020
Masci (10.1016/j.patcog.2020.107637_bib0041) 2015
Pedronette (10.1016/j.patcog.2020.107637_bib0017) 2018; 75
Zien (10.1016/j.patcog.2020.107637_bib0045) 1999; 18
Monti (10.1016/j.patcog.2020.107637_bib0040) 2017
Lu (10.1016/j.patcog.2020.107637_bib0064) 2003
Yang (10.1016/j.patcog.2020.107637_bib0058) 2016
Niepert (10.1016/j.patcog.2020.107637_bib0024) 2016
Rodriguez (10.1016/j.patcog.2020.107637_bib0047) 2003; 51
Li (10.1016/j.patcog.2020.107637_bib0044) 2017
References_xml – start-page: 6857
  year: 2018
  end-page: 6866
  ident: bib0007
  article-title: Zero-shot recognition via semantic embeddings and knowledge graphs
  publication-title: CVPR
– reference: J. Zhou, G. Cui, Z. Zhang, C. Yang, Z. Liu, M. Sun, Graph neural networks: a review of methods and applications, arXiv:
– start-page: 912
  year: 2003
  end-page: 919
  ident: bib0062
  article-title: Semi-supervised learning using gaussian fields and harmonic functions
  publication-title: ICML
– volume: 51
  start-page: 285
  year: 2003
  end-page: 297
  ident: bib0047
  article-title: On the Laplacian spectrum and walk-regular hypergraphs
  publication-title: Linear Multilinear Algebra
– start-page: 701
  year: 2014
  end-page: 710
  ident: bib0063
  article-title: DeepWalk: online learning of social representations
  publication-title: KDD
– volume: 42
  start-page: 2589
  year: 2009
  end-page: 2606
  ident: bib0068
  article-title: Graph characteristics from the heat kernel trace
  publication-title: Pattern Recognit.
– start-page: 2485
  year: 2017
  end-page: 2491
  ident: bib0029
  article-title: Column networks for collective classification.
  publication-title: AAAI
– year: 2017
  ident: bib0065
  article-title: Dynamic edge-conditioned filters in convolutional neural networks on graphs
  publication-title: CVPR
– reference: (2019).
– year: 2014
  ident: bib0019
  article-title: Spectral networks and locally connected networks on graphs
  publication-title: ICLR
– year: 2018
  ident: bib0032
  article-title: FastGCN: fast learning with graph convolutional networks via importance sampling
  publication-title: ICLR
– year: 2018
  ident: bib0037
  article-title: Adversarial attack on graph structured data
  publication-title: ICML
– volume: 13
  start-page: 1
  year: 2019
  end-page: 25
  ident: bib0039
  article-title: Attention models in graphs: a survey
  publication-title: TKDD
– year: 2016
  ident: bib0028
  article-title: Gated graph sequence neural networks
  publication-title: ICLR
– year: 2013
  ident: bib0050
  article-title: Rectifier nonlinearities improve neural network acoustic models
  publication-title: ICML
– start-page: 499
  year: 2018
  end-page: 508
  ident: bib0026
  article-title: Dual graph convolutional networks for graph-based semi-supervised classification
  publication-title: World Wide Web
– year: 2018
  ident: bib0067
  article-title: Graph convolutional policy network for goal-directed molecular graph generation
  publication-title: NeurlPS
– reference: P.W. Battaglia, J.B. Hamrick, V. Bapst, A. Sanchez-Gonzalez, V. Zambaldi, M. Malinowski, A. Tacchetti, D. Raposo, A. Santoro, R. Faulkner, et al., Relational inductive biases, deep learning, and graph networks, arXiv:
– start-page: 17
  year: 2006
  end-page: 24
  ident: bib0010
  article-title: Higher order learning with graphs
  publication-title: ICML
– start-page: 2659
  year: 2018
  end-page: 2670
  ident: bib0071
  article-title: Out of the box: reasoning with graph convolution nets for factual visual question answering
  publication-title: NeurlPS
– year: 2018
  ident: bib0008
  article-title: Graph convolutional neural networks for web-scale recommender systems
  publication-title: KDD
– year: 2015
  ident: bib0059
  article-title: Adam: a method for stochastic optimization
  publication-title: ICLR
– year: 2018
  ident: bib0031
  article-title: Graph attention networks
  publication-title: ICLR
– year: 2018
  ident: bib0030
  article-title: Representation learning on graphs with jumping knowledge networks
  publication-title: ICML
– year: 2018
  ident: bib0036
  article-title: NetGAN: generating graphs via random walks
  publication-title: ICML
– start-page: 941
  year: 2018
  end-page: 949
  ident: bib0033
  article-title: Stochastic training of graph convolutional networks with variance reduction.
  publication-title: ICML
– start-page: 3189
  year: 2016
  end-page: 3197
  ident: bib0042
  article-title: Learning shape correspondence with anisotropic convolutional neural networks
  publication-title: NeurlPS
– start-page: 5998
  year: 2017
  end-page: 6008
  ident: bib0057
  article-title: Attention is all you need
  publication-title: NeurlPS
– start-page: 1024
  year: 2017
  end-page: 1034
  ident: bib0006
  article-title: Inductive representation learning on large graphs
  publication-title: NeurlPS
– start-page: 1097
  year: 2012
  end-page: 1105
  ident: bib0001
  article-title: ImageNet classification with deep convolutional neural networks
  publication-title: NeurlPS
– reference: (2018).
– reference: B. Fatemi, P. Taslakian, D. Vazquez, D. Poole, Knowledge hypergraphs: prediction beyond binary relations, arXiv:
– year: 2015
  ident: bib0004
  article-title: Neural machine translation by jointly learning to align and translate
  publication-title: ICLR
– volume: 18
  start-page: 1389
  year: 1999
  end-page: 1399
  ident: bib0045
  article-title: Multilevel spectral hypergraph partitioning with arbitrary vertex sizes
  publication-title: IEEE Trans. Comput. Aided Des. Integr. Circuits Syst.
– volume: 75
  start-page: 161
  year: 2018
  end-page: 174
  ident: bib0017
  article-title: Unsupervised manifold learning through reciprocal kNN graph and connected components for image retrieval tasks
  publication-title: Pattern Recognit.
– start-page: 7806
  year: 2018
  end-page: 7815
  ident: bib0072
  article-title: Constrained graph variational autoencoders for molecule design
  publication-title: NeurlPS
– start-page: 2224
  year: 2015
  end-page: 2232
  ident: bib0023
  article-title: Convolutional networks on graphs for learning molecular fingerprints
  publication-title: NeurlPS
– start-page: 537
  year: 2018
  end-page: 546
  ident: bib0075
  article-title: Combinatorial optimization with graph convolutional networks and guided tree search
  publication-title: NeurlPS
– start-page: 3844
  year: 2016
  end-page: 3852
  ident: bib0021
  article-title: Convolutional neural networks on graphs with fast localized spectral filtering
  publication-title: NeurlPS
– start-page: 5987
  year: 2017
  end-page: 5995
  ident: bib0056
  article-title: Aggregated residual transformations for deep neural networks
  publication-title: CVPR
– volume: 29
  start-page: 82
  year: 2012
  end-page: 97
  ident: bib0003
  article-title: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups
  publication-title: IEEE Signal Process. Mag.
– year: 2017
  ident: bib0040
  article-title: Geometric deep learning on graphs and manifolds using mixture model CNNs
  publication-title: CVPR
– year: 2018
  ident: bib0055
  article-title: Semi-supervised user geolocation via graph convolutional networks
  publication-title: ACL
– start-page: 1993
  year: 2016
  end-page: 2001
  ident: bib0025
  article-title: Diffusion-convolutional neural networks
  publication-title: NeurlPS
– reference: (2015).
– start-page: 37
  year: 2015
  end-page: 45
  ident: bib0041
  article-title: Geodesic convolutional neural networks on Riemannian manifolds
  publication-title: ICCVW
– start-page: 593
  year: 2018
  end-page: 607
  ident: bib0066
  article-title: Modeling relational data with graph convolutional networks
  publication-title: European Semantic Web Conference
– start-page: 770
  year: 2016
  end-page: 778
  ident: bib0002
  article-title: Deep residual learning for image recognition
  publication-title: CVPR
– volume: 34
  start-page: 18
  year: 2017
  end-page: 42
  ident: bib0009
  article-title: Geometric deep learning: going beyond euclidean data
  publication-title: IEEE Signal Process. Mag.
– reference: M. Henaff, J. Bruna, Y. LeCun, Deep convolutional networks on graph-structured data, arXiv:
– year: 2017
  ident: bib0027
  article-title: Neural message passing for quantum chemistry
  publication-title: ICML
– year: 2019
  ident: bib0049
  article-title: Hypergraph neural networks
  publication-title: AAAI
– volume: 46
  start-page: 2350
  year: 2013
  end-page: 2360
  ident: bib0018
  article-title: Image re-ranking and rank aggregation based on similarity of ranked lists
  publication-title: Pattern Recognit.
– volume: 20
  start-page: 61
  year: 2009
  end-page: 80
  ident: bib0005
  article-title: The graph neural network model
  publication-title: IEEE Trans. Neural Netw.
– start-page: 3376
  year: 2010
  end-page: 3383
  ident: bib0052
  article-title: Image retrieval via probabilistic hypergraph ranking
  publication-title: CVPR
– volume: 29
  start-page: 93
  year: 2008
  ident: bib0053
  article-title: Collective classification in network data
  publication-title: AI Mag.
– year: 2016
  ident: bib0051
  article-title: Fast and accurate deep network learning by exponential linear units (ELUs)
  publication-title: ICLR
– volume: 115
  start-page: 1023
  year: 2011
  end-page: 1031
  ident: bib0069
  article-title: Learning invariant structure for object identification by using graph methods
  publication-title: CVIU
– volume: 35
  start-page: 28
  year: 2012
  end-page: 38
  ident: bib0016
  article-title: Affinity learning with diffusion on tensor product graph
  publication-title: TPAMI
– volume: 7
  start-page: 2399
  year: 2006
  end-page: 2434
  ident: bib0060
  article-title: Manifold regularization: a geometric framework for learning from labeled and unlabeled examples
  publication-title: J. Mach. Learn. Res.
– volume: 28
  start-page: 5824
  year: 2019
  end-page: 5838
  ident: bib0013
  article-title: Multimedia retrieval through unsupervised hypergraph-based manifold ranking
  publication-title: TIP
– start-page: 2014
  year: 2016
  end-page: 2023
  ident: bib0024
  article-title: Learning convolutional neural networks for graphs
  publication-title: ICML
– start-page: 2308
  year: 2017
  end-page: 2318
  ident: bib0044
  article-title: Inhomogeneous hypergraph clustering with applications
  publication-title: NeurlPS
– volume: 21
  start-page: 3262
  year: 2012
  end-page: 3272
  ident: bib0012
  article-title: Adaptive hypergraph learning and its application in image classification
  publication-title: TIP
– year: 2020
  ident: bib0014
  article-title: Deep learning on graphs: a survey
  publication-title: TKDE
– start-page: 1601
  year: 2007
  end-page: 1608
  ident: bib0048
  article-title: Learning with hypergraphs: clustering, classification, and embedding
  publication-title: NeurlPS
– start-page: 496
  year: 2003
  end-page: 503
  ident: bib0064
  article-title: Link-based classification
  publication-title: ICML
– year: 2017
  ident: bib0022
  article-title: Semi-supervised classification with graph convolutional networks
  publication-title: ICLR
– start-page: 4805
  year: 2018
  end-page: 4815
  ident: bib0034
  article-title: Hierarchical graph representation learning with differentiable pooling
  publication-title: NeurlPS
– start-page: 5694
  year: 2018
  end-page: 5703
  ident: bib0035
  article-title: GraphRNN: generating realistic graphs with deep auto-regressive models
  publication-title: ICML
– reference: C. Berge, Graphs and hypergraphs (1973).
– volume: 117
  start-page: 19
  year: 1993
  end-page: 39
  ident: bib0046
  article-title: Spectra, euclidean representations and clusterings of hypergraphs
  publication-title: Discrete Math.
– start-page: 639
  year: 2012
  end-page: 655
  ident: bib0061
  article-title: Deep Learning via Semi-supervised Embedding
  publication-title: Neural Networks: Tricks of the Trade
– year: 2016
  ident: bib0058
  article-title: Revisiting semi-supervised learning with graph embeddings
  publication-title: ICML
– volume: 98
  start-page: 107040
  year: 2020
  ident: bib0070
  article-title: Learning binary code for fast nearest subspace search
  publication-title: Pattern Recognit.
– volume: 48
  start-page: 1011
  year: 2015
  end-page: 1022
  ident: bib0074
  article-title: Low-rank matrix factorization with multiple hypergraph regularizer
  publication-title: Pattern Recognit.
– start-page: 4026
  year: 2017
  end-page: 4034
  ident: bib0011
  article-title: Re-revisiting learning on hypergraphs: confidence interval and subgradient method
  publication-title: ICML
– reference: R.K. Srivastava, K. Greff, J. Schmidhuber, Highway networks, arXiv:
– start-page: 5998
  year: 2017
  ident: 10.1016/j.patcog.2020.107637_bib0057
  article-title: Attention is all you need
– volume: 29
  start-page: 82
  issue: 6
  year: 2012
  ident: 10.1016/j.patcog.2020.107637_bib0003
  article-title: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups
  publication-title: IEEE Signal Process. Mag.
  doi: 10.1109/MSP.2012.2205597
– volume: 35
  start-page: 28
  issue: 1
  year: 2012
  ident: 10.1016/j.patcog.2020.107637_bib0016
  article-title: Affinity learning with diffusion on tensor product graph
  publication-title: TPAMI
  doi: 10.1109/TPAMI.2012.60
– start-page: 37
  year: 2015
  ident: 10.1016/j.patcog.2020.107637_bib0041
  article-title: Geodesic convolutional neural networks on Riemannian manifolds
– volume: 51
  start-page: 285
  issue: 3
  year: 2003
  ident: 10.1016/j.patcog.2020.107637_bib0047
  article-title: On the Laplacian spectrum and walk-regular hypergraphs
  publication-title: Linear Multilinear Algebra
  doi: 10.1080/0308108031000084374
– start-page: 912
  year: 2003
  ident: 10.1016/j.patcog.2020.107637_bib0062
  article-title: Semi-supervised learning using gaussian fields and harmonic functions
– volume: 21
  start-page: 3262
  issue: 7
  year: 2012
  ident: 10.1016/j.patcog.2020.107637_bib0012
  article-title: Adaptive hypergraph learning and its application in image classification
  publication-title: TIP
– start-page: 496
  year: 2003
  ident: 10.1016/j.patcog.2020.107637_bib0064
  article-title: Link-based classification
– start-page: 2659
  year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0071
  article-title: Out of the box: reasoning with graph convolution nets for factual visual question answering
– volume: 20
  start-page: 61
  issue: 1
  year: 2009
  ident: 10.1016/j.patcog.2020.107637_bib0005
  article-title: The graph neural network model
  publication-title: IEEE Trans. Neural Netw.
  doi: 10.1109/TNN.2008.2005605
– start-page: 1024
  year: 2017
  ident: 10.1016/j.patcog.2020.107637_bib0006
  article-title: Inductive representation learning on large graphs
– year: 2017
  ident: 10.1016/j.patcog.2020.107637_bib0022
  article-title: Semi-supervised classification with graph convolutional networks
– volume: 48
  start-page: 1011
  issue: 3
  year: 2015
  ident: 10.1016/j.patcog.2020.107637_bib0074
  article-title: Low-rank matrix factorization with multiple hypergraph regularizer
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2014.09.002
– volume: 28
  start-page: 5824
  issue: 12
  year: 2019
  ident: 10.1016/j.patcog.2020.107637_bib0013
  article-title: Multimedia retrieval through unsupervised hypergraph-based manifold ranking
  publication-title: TIP
– volume: 13
  start-page: 1
  issue: 6
  year: 2019
  ident: 10.1016/j.patcog.2020.107637_bib0039
  article-title: Attention models in graphs: a survey
  publication-title: TKDD
  doi: 10.1145/3363574
– volume: 18
  start-page: 1389
  issue: 9
  year: 1999
  ident: 10.1016/j.patcog.2020.107637_bib0045
  article-title: Multilevel spectral hypergraph partitioning with arbitrary vertex sizes
  publication-title: IEEE Trans. Comput. Aided Des. Integr. Circuits Syst.
  doi: 10.1109/43.784130
– start-page: 1601
  year: 2007
  ident: 10.1016/j.patcog.2020.107637_bib0048
  article-title: Learning with hypergraphs: clustering, classification, and embedding
– start-page: 537
  year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0075
  article-title: Combinatorial optimization with graph convolutional networks and guided tree search
– start-page: 5987
  year: 2017
  ident: 10.1016/j.patcog.2020.107637_bib0056
  article-title: Aggregated residual transformations for deep neural networks
– year: 2016
  ident: 10.1016/j.patcog.2020.107637_bib0058
  article-title: Revisiting semi-supervised learning with graph embeddings
– start-page: 4026
  year: 2017
  ident: 10.1016/j.patcog.2020.107637_bib0011
  article-title: Re-revisiting learning on hypergraphs: confidence interval and subgradient method
– start-page: 941
  year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0033
  article-title: Stochastic training of graph convolutional networks with variance reduction.
– year: 2015
  ident: 10.1016/j.patcog.2020.107637_bib0004
  article-title: Neural machine translation by jointly learning to align and translate
– year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0031
  article-title: Graph attention networks
– year: 2016
  ident: 10.1016/j.patcog.2020.107637_bib0028
  article-title: Gated graph sequence neural networks
– ident: 10.1016/j.patcog.2020.107637_bib0015
– year: 2019
  ident: 10.1016/j.patcog.2020.107637_bib0049
  article-title: Hypergraph neural networks
– ident: 10.1016/j.patcog.2020.107637_bib0043
– start-page: 1993
  year: 2016
  ident: 10.1016/j.patcog.2020.107637_bib0025
  article-title: Diffusion-convolutional neural networks
– volume: 98
  start-page: 107040
  year: 2020
  ident: 10.1016/j.patcog.2020.107637_bib0070
  article-title: Learning binary code for fast nearest subspace search
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2019.107040
– volume: 7
  start-page: 2399
  year: 2006
  ident: 10.1016/j.patcog.2020.107637_bib0060
  article-title: Manifold regularization: a geometric framework for learning from labeled and unlabeled examples
  publication-title: J. Mach. Learn. Res.
– year: 2017
  ident: 10.1016/j.patcog.2020.107637_bib0027
  article-title: Neural message passing for quantum chemistry
– start-page: 639
  year: 2012
  ident: 10.1016/j.patcog.2020.107637_bib0061
  article-title: Deep Learning via Semi-supervised Embedding
– year: 2020
  ident: 10.1016/j.patcog.2020.107637_bib0014
  article-title: Deep learning on graphs: a survey
  publication-title: TKDE
– ident: 10.1016/j.patcog.2020.107637_bib0054
– start-page: 3189
  year: 2016
  ident: 10.1016/j.patcog.2020.107637_bib0042
  article-title: Learning shape correspondence with anisotropic convolutional neural networks
– volume: 42
  start-page: 2589
  issue: 11
  year: 2009
  ident: 10.1016/j.patcog.2020.107637_bib0068
  article-title: Graph characteristics from the heat kernel trace
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2008.12.029
– volume: 46
  start-page: 2350
  issue: 8
  year: 2013
  ident: 10.1016/j.patcog.2020.107637_bib0018
  article-title: Image re-ranking and rank aggregation based on similarity of ranked lists
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2013.01.004
– year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0032
  article-title: FastGCN: fast learning with graph convolutional networks via importance sampling
– start-page: 1097
  year: 2012
  ident: 10.1016/j.patcog.2020.107637_bib0001
  article-title: ImageNet classification with deep convolutional neural networks
– volume: 117
  start-page: 19
  issue: 1–3
  year: 1993
  ident: 10.1016/j.patcog.2020.107637_bib0046
  article-title: Spectra, euclidean representations and clusterings of hypergraphs
  publication-title: Discrete Math.
  doi: 10.1016/0012-365X(93)90322-K
– year: 2017
  ident: 10.1016/j.patcog.2020.107637_bib0065
  article-title: Dynamic edge-conditioned filters in convolutional neural networks on graphs
– start-page: 2485
  year: 2017
  ident: 10.1016/j.patcog.2020.107637_bib0029
  article-title: Column networks for collective classification.
– year: 2015
  ident: 10.1016/j.patcog.2020.107637_bib0059
  article-title: Adam: a method for stochastic optimization
– start-page: 593
  year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0066
  article-title: Modeling relational data with graph convolutional networks
– volume: 34
  start-page: 18
  issue: 4
  year: 2017
  ident: 10.1016/j.patcog.2020.107637_bib0009
  article-title: Geometric deep learning: going beyond euclidean data
  publication-title: IEEE Signal Process. Mag.
  doi: 10.1109/MSP.2017.2693418
– start-page: 3844
  year: 2016
  ident: 10.1016/j.patcog.2020.107637_bib0021
  article-title: Convolutional neural networks on graphs with fast localized spectral filtering
– start-page: 5694
  year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0035
  article-title: GraphRNN: generating realistic graphs with deep auto-regressive models
– start-page: 2308
  year: 2017
  ident: 10.1016/j.patcog.2020.107637_bib0044
  article-title: Inhomogeneous hypergraph clustering with applications
– year: 2014
  ident: 10.1016/j.patcog.2020.107637_bib0019
  article-title: Spectral networks and locally connected networks on graphs
– volume: 29
  start-page: 93
  issue: 3
  year: 2008
  ident: 10.1016/j.patcog.2020.107637_bib0053
  article-title: Collective classification in network data
  publication-title: AI Mag.
– year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0067
  article-title: Graph convolutional policy network for goal-directed molecular graph generation
– start-page: 17
  year: 2006
  ident: 10.1016/j.patcog.2020.107637_bib0010
  article-title: Higher order learning with graphs
– year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0036
  article-title: NetGAN: generating graphs via random walks
– start-page: 2224
  year: 2015
  ident: 10.1016/j.patcog.2020.107637_bib0023
  article-title: Convolutional networks on graphs for learning molecular fingerprints
– year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0008
  article-title: Graph convolutional neural networks for web-scale recommender systems
– year: 2016
  ident: 10.1016/j.patcog.2020.107637_bib0051
  article-title: Fast and accurate deep network learning by exponential linear units (ELUs)
– year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0037
  article-title: Adversarial attack on graph structured data
– ident: 10.1016/j.patcog.2020.107637_bib0073
  doi: 10.24963/ijcai.2020/303
– year: 2017
  ident: 10.1016/j.patcog.2020.107637_bib0040
  article-title: Geometric deep learning on graphs and manifolds using mixture model CNNs
– start-page: 3376
  year: 2010
  ident: 10.1016/j.patcog.2020.107637_bib0052
  article-title: Image retrieval via probabilistic hypergraph ranking
– volume: 115
  start-page: 1023
  issue: 7
  year: 2011
  ident: 10.1016/j.patcog.2020.107637_bib0069
  article-title: Learning invariant structure for object identification by using graph methods
  publication-title: CVIU
– ident: 10.1016/j.patcog.2020.107637_bib0038
– year: 2013
  ident: 10.1016/j.patcog.2020.107637_bib0050
  article-title: Rectifier nonlinearities improve neural network acoustic models
– start-page: 499
  year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0026
  article-title: Dual graph convolutional networks for graph-based semi-supervised classification
– start-page: 6857
  year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0007
  article-title: Zero-shot recognition via semantic embeddings and knowledge graphs
– start-page: 4805
  year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0034
  article-title: Hierarchical graph representation learning with differentiable pooling
– start-page: 701
  year: 2014
  ident: 10.1016/j.patcog.2020.107637_bib0063
  article-title: DeepWalk: online learning of social representations
– start-page: 7806
  year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0072
  article-title: Constrained graph variational autoencoders for molecule design
– volume: 75
  start-page: 161
  year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0017
  article-title: Unsupervised manifold learning through reciprocal kNN graph and connected components for image retrieval tasks
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2017.05.009
– start-page: 2014
  year: 2016
  ident: 10.1016/j.patcog.2020.107637_bib0024
  article-title: Learning convolutional neural networks for graphs
– year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0055
  article-title: Semi-supervised user geolocation via graph convolutional networks
– start-page: 770
  year: 2016
  ident: 10.1016/j.patcog.2020.107637_bib0002
  article-title: Deep residual learning for image recognition
– ident: 10.1016/j.patcog.2020.107637_bib0020
– year: 2018
  ident: 10.1016/j.patcog.2020.107637_bib0030
  article-title: Representation learning on graphs with jumping knowledge networks
SSID ssj0017142
Score 2.7308648
Snippet •Hypergraph convolution defines a basic convolutional operator in a hypergraph. It enables an efficient information propagation between vertices by fully...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 107637
SubjectTerms Graph learning
Graph neural networks
Hypergraph learning
Semi-supervised learning
Title Hypergraph convolution and hypergraph attention
URI https://dx.doi.org/10.1016/j.patcog.2020.107637
Volume 110
WOSCitedRecordID wos000585303400005&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1873-5142
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017142
  issn: 0031-3203
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3JTsMwELWAcuDCjtiVAzeUksSOnRwLoioIIaQWqbcoy4S2QmmVFtTPZxI7SyliOXCJIidxlueM39jjN4RcUMcCFgRct-LI1VnA8J-DyNHjkMc8NEOXRrm6_oN4fHT6ffdJJf6b5ukERJI487k7-VeosQzBzpbO_gHuslIswH0EHbcIO25_BXwHPcs016HOQ8rVvfJJgkF1KJPVTEpQFDt9ysU2swUuKqqomqO_lmmru2PV09XHmtswHLxVw9VpWo3UXHaa3WZ9ZMEyi2DkylpSU6eWQRespYpClfYOnUcuRVuWTLEcFRg1J9iljF_QE7eywuL0ReXrTz1SGSdYhKCNPFmLl9XiyVpWScMStouWrNG6u-3fl3NHwmRSI149fbFgMo_qW36arwlJjWT0tsmm8g60lkR1h6xAsku2iswbmjLEe-SqAlmrgawhyFoFslaCvE-e27e9m46uUl_oIfpwM92MueEAR_pgAgAFCJBZBSAYRBFSQtzjNlguGCJCK8pt5iMtzqSkeGSFYBv0gKwl4wQOiebHvsFiP_sjKWO-4XNfhGYsIEJrjmz9iNDi_b1Q6cJn6Uleve--_hHRy6smUhflh_NF8Wk9xe0kZ_OwvXx75fEf73RCNqrGfErWZukbnJH18H02nKbnqrF8ABz5cIk
linkProvider Elsevier
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=Hypergraph+convolution+and+hypergraph+attention&rft.jtitle=Pattern+recognition&rft.au=Bai%2C+Song&rft.au=Zhang%2C+Feihu&rft.au=Torr%2C+Philip+H.S.&rft.date=2021-02-01&rft.issn=0031-3203&rft.volume=110&rft.spage=107637&rft_id=info:doi/10.1016%2Fj.patcog.2020.107637&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_patcog_2020_107637
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon