{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/geom-gcn-geometric-graph-convolutional-1","title":"Geom-GCN: Geometric Graph Convolutional Networks","arxiv_id":"2002.05287","date":"2020-02-13","proceeding":"ICLR 2020 1","authors":["Hongbin Pei","Bingzhe Wei","Kevin Chen-Chuan Chang","Yu Lei","Bo Yang"],"abstract":"Message-passing neural networks (MPNNs) have been successfully applied to representation learning on graphs in a variety of real-world applications. However, two fundamental weaknesses of MPNNs' aggregators limit their ability to represent graph-structured data: losing the structural information of nodes in neighborhoods and lacking the ability to capture long-range dependencies in disassortative graphs. Few studies have noticed the weaknesses from different perspectives. From the observations on classical neural network and network geometry, we propose a novel geometric aggregation scheme for graph neural networks to overcome the two weaknesses. The behind basic idea is the aggregation on a graph can benefit from a continuous space underlying the graph. The proposed aggregation scheme is permutation-invariant and consists of three modules, node embedding, structural neighborhood, and bi-level aggregation. We also present an implementation of the scheme in graph convolutional networks, termed Geom-GCN (Geometric Graph Convolutional Networks), to perform transductive learning on graphs. Experimental results show the proposed Geom-GCN achieved state-of-the-art performance on a wide range of open datasets of graphs. Code is available at https://github.com/graphdml-uiuc-jlu/geom-gcn.","url_abs":"https://arxiv.org/abs/2002.05287v2","url_pdf":"https://arxiv.org/pdf/2002.05287v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"geom-gcn-geometric-graph-convolutional-1","repo_url":"https://github.com/graphdml-uiuc-jlu/geom-gcn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"geom-gcn-geometric-graph-convolutional-1","repo_url":"https://github.com/KAIDI3270/Geom_GCN_pytorch_implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"geom-gcn-geometric-graph-convolutional-1","repo_url":"https://github.com/alexfanjn/geomgcn_pyg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"geom-gcn-geometric-graph-convolutional-1","repo_url":"https://github.com/bingzhewei/geom-gcn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"node-classification-on-non-homophilic","task_name":"Node Classification on Non-Homophilic (Heterophilic) Graphs"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"transductive-learning","task_name":"Transductive Learning"}],"methods":[],"datasets_introduced":[{"slug":"chameleon-48-32-20-fixed-splits","name":"Chameleon (48%/32%/20% fixed splits)","full_name":""},{"slug":"citeseer-48-32-20-fixed-splits","name":"Citeseer (48%/32%/20% fixed splits)","full_name":""},{"slug":"cora-48-32-20-fixed-splits","name":"Cora (48%/32%/20% fixed splits)","full_name":""},{"slug":"cornell-48-32-20-fixed-splits","name":"Cornell (48%/32%/20% fixed splits)","full_name":""},{"slug":"film-48-32-20-fixed-splits","name":"Film(48%/32%/20% fixed splits)","full_name":""},{"slug":"pubmed-48-32-20-fixed-splits","name":"PubMed (48%/32%/20% fixed splits)","full_name":""},{"slug":"squirrel-48-32-20-fixed-splits","name":"Squirrel (48%/32%/20% fixed splits)","full_name":""},{"slug":"texas-48-32-20-fixed-splits","name":"Texas (48%/32%/20% fixed splits)","full_name":""},{"slug":"wisconsin-48-32-20-fixed-splits","name":"Wisconsin (48%/32%/20% fixed splits)","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-actor","task":"Node Classification","dataset":"Actor","model":"Geom-GCN-P","rank_in_archive_order":56,"of":62,"metrics":{"Accuracy":"31.63"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-actor","task":"Node Classification","dataset":"Actor","model":"Geom-GCN-S","rank_in_archive_order":58,"of":62,"metrics":{"Accuracy":"30.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-actor","task":"Node Classification","dataset":"Actor","model":"Geom-GCN-I","rank_in_archive_order":61,"of":62,"metrics":{"Accuracy":"29.09"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"Geom-GCN-P","rank_in_archive_order":50,"of":61,"metrics":{"Accuracy":"60.9"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"Geom-GCN-I","rank_in_archive_order":52,"of":61,"metrics":{"Accuracy":"60.31"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"Geom-GCN-S","rank_in_archive_order":53,"of":61,"metrics":{"Accuracy":"59.96"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon-60-20-20","task":"Node Classification","dataset":"Chameleon (60%/20%/20% random splits)","model":"Geom-GCN*","rank_in_archive_order":29,"of":38,"metrics":{"1:1 Accuracy":"60.9"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-60-20-20","task":"Node Classification","dataset":"CiteSeer (60%/20%/20% random splits)","model":"Geom-GCN*","rank_in_archive_order":26,"of":33,"metrics":{"1:1 Accuracy":"77.99"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-48-32-20","task":"Node Classification","dataset":"Citeseer (48%/32%/20% fixed splits)","model":"Geom-GCN","rank_in_archive_order":1,"of":26,"metrics":{"1:1 Accuracy":"78.02 ± 1.15"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-48-32-20-fixed","task":"Node Classification","dataset":"Cora (48%/32%/20% fixed splits)","model":"Geom-GCN","rank_in_archive_order":23,"of":26,"metrics":{"1:1 Accuracy":"85.35 ± 1.57"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-60-20-20-random","task":"Node Classification","dataset":"Cora (60%/20%/20% random splits)","model":"Geom-GCN*","rank_in_archive_order":27,"of":33,"metrics":{"1:1 Accuracy":"85.27"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"Geom-GCN-P","rank_in_archive_order":53,"of":60,"metrics":{"Accuracy":"60.81"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"Geom-GCN-I","rank_in_archive_order":56,"of":60,"metrics":{"Accuracy":"56.76"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"Geom-GCN-S","rank_in_archive_order":57,"of":60,"metrics":{"Accuracy":"55.68"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell-60-20-20","task":"Node Classification","dataset":"Cornell (60%/20%/20% random splits)","model":"Geom-GCN*","rank_in_archive_order":35,"of":36,"metrics":{"1:1 Accuracy":"60.81"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-film-60-20-20-random","task":"Node Classification","dataset":"Film (60%/20%/20% random splits)","model":"Geom-GCN*","rank_in_archive_order":34,"of":37,"metrics":{"1:1 Accuracy":"31.63"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-48-32-20-fixed","task":"Node Classification","dataset":"PubMed (48%/32%/20% fixed splits)","model":"Geom-GCN","rank_in_archive_order":2,"of":26,"metrics":{"1:1 Accuracy":"89.95 ± 0.47"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-60-20-20-random","task":"Node Classification","dataset":"PubMed (60%/20%/20% random splits)","model":"Geom-GCN*","rank_in_archive_order":17,"of":37,"metrics":{"1:1 Accuracy":"90.05"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel","task":"Node Classification","dataset":"Squirrel","model":"Geom-GCN-P","rank_in_archive_order":52,"of":59,"metrics":{"Accuracy":"38.14"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel","task":"Node Classification","dataset":"Squirrel","model":"Geom-GCN-S","rank_in_archive_order":54,"of":59,"metrics":{"Accuracy":"36.24"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel","task":"Node Classification","dataset":"Squirrel","model":"Geom-GCN-I","rank_in_archive_order":56,"of":59,"metrics":{"Accuracy":"33.32"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel-60-20-20","task":"Node Classification","dataset":"Squirrel (60%/20%/20% random splits)","model":"Geom-GCN*","rank_in_archive_order":33,"of":37,"metrics":{"1:1 Accuracy":"38.14"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset":"Texas","model":"Geom-GCN-P","rank_in_archive_order":56,"of":62,"metrics":{"Accuracy":"67.57"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset":"Texas","model":"Geom-GCN-S","rank_in_archive_order":60,"of":62,"metrics":{"Accuracy":"59.73"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset":"Texas","model":"Geom-GCN-I","rank_in_archive_order":61,"of":62,"metrics":{"Accuracy":"57.58"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas-60-20-20-random","task":"Node Classification","dataset":"Texas (60%/20%/20% random splits)","model":"Geom-GCN*","rank_in_archive_order":36,"of":36,"metrics":{"1:1 Accuracy":"67.57"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset":"Wisconsin","model":"Geom-GCN-P","rank_in_archive_order":58,"of":63,"metrics":{"Accuracy":"64.12"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset":"Wisconsin","model":"Geom-GCN-I","rank_in_archive_order":60,"of":63,"metrics":{"Accuracy":"58.24"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset":"Wisconsin","model":"Geom-GCN-S","rank_in_archive_order":62,"of":63,"metrics":{"Accuracy":"56.67"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin-60-20-20","task":"Node Classification","dataset":"Wisconsin (60%/20%/20% random splits)","model":"Geom-GCN*","rank_in_archive_order":34,"of":35,"metrics":{"1:1 Accuracy":"64.12"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-11","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Chameleon (48%/32%/20% fixed splits)","model":"Geom-GCN","rank_in_archive_order":26,"of":29,"metrics":{"1:1 Accuracy":"60.00 ± 2.81"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-4","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Chameleon(60%/20%/20% random splits)","model":"Geom-GCN*","rank_in_archive_order":24,"of":32,"metrics":{"1:1 Accuracy":"60.9"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-7","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Cornell (48%/32%/20% fixed splits)","model":"Geom-GCN","rank_in_archive_order":25,"of":27,"metrics":{"1:1 Accuracy":"60.54 ± 3.67"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Cornell (60%/20%/20% random splits)","model":"Geom-GCN*","rank_in_archive_order":32,"of":33,"metrics":{"1:1 Accuracy":"60.81"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-10","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Film(48%/32%/20% fixed splits)","model":"Geom-GCN","rank_in_archive_order":25,"of":26,"metrics":{"1:1 Accuracy":"31.59 ± 1.15"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-12","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Squirrel (48%/32%/20% fixed splits)","model":"Geom-GCN","rank_in_archive_order":26,"of":29,"metrics":{"1:1 Accuracy":"38.15 ± 0.92"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-9","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Texas (48%/32%/20% fixed splits)","model":"Geom-GCN","rank_in_archive_order":24,"of":26,"metrics":{"1:1 Accuracy":"66.76 ± 2.72"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-2","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Texas(60%/20%/20% random splits)","model":"Geom-GCN*","rank_in_archive_order":32,"of":32,"metrics":{"1:1 Accuracy":"67.57"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-8","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Wisconsin (48%/32%/20% fixed splits)","model":"Geom-GCN","rank_in_archive_order":24,"of":26,"metrics":{"1:1 Accuracy":"64.51 ± 3.66"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-1","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Wisconsin(60%/20%/20% random splits)","model":"Geom-GCN*","rank_in_archive_order":31,"of":32,"metrics":{"1:1 Accuracy":"64.12"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.05287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.05287"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/graphdml-uiuc-jlu/geom-gcn","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bingzhewei/geom-gcn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexfanjn/geomgcn_pyg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KAIDI3270/Geom_GCN_pytorch_implementation","reach":{"status":"ok"}}],"summary":{"ran":2,"ran_draft_wrong":4,"ran_honours":1},"by_repo_kind":{"listed":{"samples":7,"ran":7,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":7,"samples":[{"code_sha256_prefix":"fdae60f85c7b410e","entry":"GeomGCN","repo":"alexfanjn/geomgcn_pyg","repo_kind":"listed","path":"model.py","file_url":"https://github.com/alexfanjn/geomgcn_pyg/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fdae60f85c7b410e"}},{"code_sha256_prefix":"2ef6fd9f93ca6ebf","entry":"GeomGCN_layer","repo":"alexfanjn/geomgcn_pyg","repo_kind":"listed","path":"model.py","file_url":"https://github.com/alexfanjn/geomgcn_pyg/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2ef6fd9f93ca6ebf"}},{"code_sha256_prefix":"c187bf050bb2c556","entry":"edge_index_to_sparse_tensor_adj","repo":"alexfanjn/geomgcn_pyg","repo_kind":"listed","path":"model.py","file_url":"https://github.com/alexfanjn/geomgcn_pyg/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c187bf050bb2c556"}},{"code_sha256_prefix":"0626d35807929da7","entry":"gcn_norm","repo":"alexfanjn/geomgcn_pyg","repo_kind":"listed","path":"model.py","file_url":"https://github.com/alexfanjn/geomgcn_pyg/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0626d35807929da7"}},{"code_sha256_prefix":"32302e598b1afb70","entry":"load_data","repo":"bingzhewei/geom-gcn","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/bingzhewei/geom-gcn/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"32302e598b1afb70"}},{"code_sha256_prefix":"dfd091f34611a47a","entry":"parse_index_file","repo":"bingzhewei/geom-gcn","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/bingzhewei/geom-gcn/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dfd091f34611a47a"}},{"code_sha256_prefix":"61cb7d8c95b55c0c","entry":"sample_mask","repo":"bingzhewei/geom-gcn","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/bingzhewei/geom-gcn/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"61cb7d8c95b55c0c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}