{"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/convolutional-neural-networks-on-graphs-with","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","arxiv_id":"1606.09375","date":"2016-06-30","proceeding":"NeurIPS 2016 12","authors":["Michaël Defferrard","Xavier Bresson","Pierre Vandergheynst"],"abstract":"In this work, we are interested in generalizing convolutional neural networks\n(CNNs) from low-dimensional regular grids, where image, video and speech are\nrepresented, to high-dimensional irregular domains, such as social networks,\nbrain connectomes or words' embedding, represented by graphs. We present a\nformulation of CNNs in the context of spectral graph theory, which provides the\nnecessary mathematical background and efficient numerical schemes to design\nfast localized convolutional filters on graphs. Importantly, the proposed\ntechnique offers the same linear computational complexity and constant learning\ncomplexity as classical CNNs, while being universal to any graph structure.\nExperiments on MNIST and 20NEWS demonstrate the ability of this novel deep\nlearning system to learn local, stationary, and compositional features on\ngraphs.","url_abs":"http://arxiv.org/abs/1606.09375v3","url_pdf":"http://arxiv.org/pdf/1606.09375v3.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":"convolutional-neural-networks-on-graphs-with","repo_url":"https://github.com/mdeff/cnn_graph","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"convolutional-neural-networks-on-graphs-with","repo_url":"https://github.com/ajbisberg/gcn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"convolutional-neural-networks-on-graphs-with","repo_url":"https://github.com/hazdzz/ChebyNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"convolutional-neural-networks-on-graphs-with","repo_url":"https://github.com/mdeff/paper-cnn-graph-nips2016","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"CC-BY-4.0"}},{"paper_slug":"convolutional-neural-networks-on-graphs-with","repo_url":"https://github.com/selmiss/gp-tlstgcn","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":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"}],"methods":[{"method_slug":"chebnet","method_name":"ChebNet"}],"datasets_introduced":[],"methods_introduced":[{"slug":"chebnet","name":"ChebNet","full_name":"ChebNet"}],"results":[{"leaderboard":"/sota/graph-property-prediction-on-ogbg-molpcba","task":"Graph Property Prediction","dataset":"ogbg-molpcba","model":"ChebNet","rank_in_archive_order":32,"of":36,"metrics":{"Ext. data":"No","Number of params":"1475003","Test AP":"0.2306 ± 0.0016","Validation AP":"0.2372 ± 0.0018"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-05","task":"Node Classification","dataset":"CiteSeer (0.5%)","model":"ChebyNet","rank_in_archive_order":10,"of":14,"metrics":{"Accuracy":"45.3%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-1","task":"Node Classification","dataset":"CiteSeer (1%)","model":"ChebyNet","rank_in_archive_order":10,"of":14,"metrics":{"Accuracy":"59.4%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-with-public","task":"Node Classification","dataset":"CiteSeer with Public Split: fixed 20 nodes per class","model":"ChebyNet","rank_in_archive_order":33,"of":40,"metrics":{"Accuracy":"70.1%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"ChebNet","rank_in_archive_order":60,"of":71,"metrics":{"Accuracy":"69.8%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora","task":"Node Classification","dataset":"Cora","model":"ChebNet","rank_in_archive_order":62,"of":73,"metrics":{"Accuracy":"81.2%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-05","task":"Node Classification","dataset":"Cora (0.5%)","model":"ChebyNet","rank_in_archive_order":15,"of":15,"metrics":{"Accuracy":"33.9%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-1","task":"Node Classification","dataset":"Cora (1%)","model":"ChebyNet","rank_in_archive_order":15,"of":15,"metrics":{"Accuracy":"44.2%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-3","task":"Node Classification","dataset":"Cora (3%)","model":"ChebyNet","rank_in_archive_order":14,"of":15,"metrics":{"Accuracy":"62.1%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-with-public-split","task":"Node Classification","dataset":"Cora with Public Split: fixed 20 nodes per class","model":"ChebyNet","rank_in_archive_order":33,"of":36,"metrics":{"Accuracy":"78.0%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-003","task":"Node Classification","dataset":"PubMed (0.03%)","model":"ChebyNet","rank_in_archive_order":14,"of":14,"metrics":{"Accuracy":"45.3%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-005","task":"Node Classification","dataset":"PubMed (0.05%)","model":"ChebyNet","rank_in_archive_order":14,"of":14,"metrics":{"Accuracy":"48.2%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-01","task":"Node Classification","dataset":"PubMed (0.1%)","model":"ChebyNet","rank_in_archive_order":14,"of":14,"metrics":{"Accuracy":"55.2%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-with-public","task":"Node Classification","dataset":"PubMed with Public Split: fixed 20 nodes per class","model":"ChebyNet","rank_in_archive_order":37,"of":37,"metrics":{"Accuracy":"69.8%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"ChebNet","rank_in_archive_order":64,"of":70,"metrics":{"Accuracy":"74.4%"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-sbu","task":"Skeleton Based Action Recognition","dataset":"SBU / SBU-Refine","model":"ChebyNet","rank_in_archive_order":4,"of":9,"metrics":{"Accuracy":"96.00%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1606.09375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.09375"}},"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/mdeff/cnn_graph","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hazdzz/ChebyNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mdeff/paper-cnn-graph-nips2016","reach":{"status":"ok","spdx":"CC-BY-4.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ajbisberg/gcn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/selmiss/gp-tlstgcn","reach":null}],"summary":{"ran":2,"unverified":4},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1},"listed":{"samples":4,"ran":2,"repositories":3}},"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":2,"samples":[{"code_sha256_prefix":"030e43e156dbda0e","entry":"ChebGraphConv","repo":"hazdzz/ChebyNet","repo_kind":"listed","path":"model/layers.py","file_url":"https://github.com/hazdzz/ChebyNet/blob/HEAD/model/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"LGPL-2.1","inline_ok":false,"mcp_get_code":{"code_sha256":"030e43e156dbda0e"}},{"code_sha256_prefix":"c6ca6754d762f682","entry":"ChebGraphConv","repo":"selmiss/gp-tlstgcn","repo_kind":"listed","path":"model/layers.py","file_url":"https://github.com/selmiss/gp-tlstgcn/blob/HEAD/model/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"LGPL-2.1","inline_ok":false,"mcp_get_code":{"code_sha256":"c6ca6754d762f682"}},{"code_sha256_prefix":"d033d441612bfa4b","entry":"GraphConvolution","repo":"ajbisberg/gcn","repo_kind":"listed","path":"gcn/layers.py","file_url":"https://github.com/ajbisberg/gcn/blob/HEAD/gcn/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d033d441612bfa4b"}},{"code_sha256_prefix":"e643d1f9db59f99c","entry":"Layer","repo":"ajbisberg/gcn","repo_kind":"listed","path":"gcn/layers.py","file_url":"https://github.com/ajbisberg/gcn/blob/HEAD/gcn/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e643d1f9db59f99c"}},{"code_sha256_prefix":"fcd0e1963d1c958e","entry":"base_model","repo":"mdeff/cnn_graph","repo_kind":"official","path":"lib/models.py","file_url":"https://github.com/mdeff/cnn_graph/blob/HEAD/lib/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fcd0e1963d1c958e"}},{"code_sha256_prefix":"9cb375d9b8adcbdf","entry":"cgcnn2_2","repo":"mdeff/cnn_graph","repo_kind":"official","path":"lib/models.py","file_url":"https://github.com/mdeff/cnn_graph/blob/HEAD/lib/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9cb375d9b8adcbdf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}