{"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/diffusion-improves-graph-learning-1","title":"Diffusion Improves Graph Learning","arxiv_id":"1911.05485","date":"2019-10-28","proceeding":"NeurIPS 2019 12","authors":["Johannes Gasteiger","Stefan Weißenberger","Stephan Günnemann"],"abstract":"Graph convolution is the core of most Graph Neural Networks (GNNs) and usually approximated by message passing between direct (one-hop) neighbors. In this work, we remove the restriction of using only the direct neighbors by introducing a powerful, yet spatially localized graph convolution: Graph diffusion convolution (GDC). GDC leverages generalized graph diffusion, examples of which are the heat kernel and personalized PageRank. It alleviates the problem of noisy and often arbitrarily defined edges in real graphs. We show that GDC is closely related to spectral-based models and thus combines the strengths of both spatial (message passing) and spectral methods. We demonstrate that replacing message passing with graph diffusion convolution consistently leads to significant performance improvements across a wide range of models on both supervised and unsupervised tasks and a variety of datasets. Furthermore, GDC is not limited to GNNs but can trivially be combined with any graph-based model or algorithm (e.g. spectral clustering) without requiring any changes to the latter or affecting its computational complexity. Our implementation is available online.","url_abs":"https://arxiv.org/abs/1911.05485v6","url_pdf":"https://arxiv.org/pdf/1911.05485v6.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":"diffusion-improves-graph-learning-1","repo_url":"https://github.com/klicperajo/gdc","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"diffusion-improves-graph-learning-1","repo_url":"https://github.com/hazdzz/GDC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"LGPL-2.1"}},{"paper_slug":"diffusion-improves-graph-learning-1","repo_url":"https://github.com/jhngjng/naq-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-amz-comp","task":"Node Classification","dataset":"AMZ Comp","model":"GCN (Heat Diffusion)","rank_in_archive_order":3,"of":7,"metrics":{"Accuracy":"86.77%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-amz-photo","task":"Node Classification","dataset":"AMZ Photo","model":"JK (Heat Diffusion)","rank_in_archive_order":10,"of":14,"metrics":{"Accuracy":"92.93%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"GCN (PPR Diffusion)","rank_in_archive_order":34,"of":71,"metrics":{"Accuracy":"73.35%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-coauthor-cs","task":"Node Classification","dataset":"Coauthor CS","model":"GCN (PPR Diffusion)","rank_in_archive_order":18,"of":24,"metrics":{"Accuracy":"93.01%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"JK (Heat Diffusion)","rank_in_archive_order":36,"of":70,"metrics":{"Accuracy":"79.95%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.05485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.05485"}},"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/hazdzz/GDC","reach":{"status":"ok","spdx":"LGPL-2.1"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/klicperajo/gdc","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jhngjng/naq-pytorch","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"c68140584cc0e991","entry":"get_component","repo":"klicperajo/gdc","repo_kind":"official","path":"data.py","file_url":"https://github.com/klicperajo/gdc/blob/HEAD/data.py","link_basis":"harvester_set","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":"c68140584cc0e991"}},{"code_sha256_prefix":"80bcc0c354de813f","entry":"get_dataset","repo":"klicperajo/gdc","repo_kind":"official","path":"data.py","file_url":"https://github.com/klicperajo/gdc/blob/HEAD/data.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":"80bcc0c354de813f"}},{"code_sha256_prefix":"b36878b25e3455a3","entry":"get_largest_connected_component","repo":"klicperajo/gdc","repo_kind":"official","path":"data.py","file_url":"https://github.com/klicperajo/gdc/blob/HEAD/data.py","link_basis":"harvester_set","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":"b36878b25e3455a3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}