{"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/deep-graph-matching-consensus-1","title":"Deep Graph Matching Consensus","arxiv_id":"2001.09621","date":"2020-01-27","proceeding":"ICLR 2020 1","authors":["Matthias Fey","Jan E. Lenssen","Christopher Morris","Jonathan Masci","Nils M. Kriege"],"abstract":"This work presents a two-stage neural architecture for learning and refining structural correspondences between graphs. First, we use localized node embeddings computed by a graph neural network to obtain an initial ranking of soft correspondences between nodes. Secondly, we employ synchronous message passing networks to iteratively re-rank the soft correspondences to reach a matching consensus in local neighborhoods between graphs. We show, theoretically and empirically, that our message passing scheme computes a well-founded measure of consensus for corresponding neighborhoods, which is then used to guide the iterative re-ranking process. Our purely local and sparsity-aware architecture scales well to large, real-world inputs while still being able to recover global correspondences consistently. We demonstrate the practical effectiveness of our method on real-world tasks from the fields of computer vision and entity alignment between knowledge graphs, on which we improve upon the current state-of-the-art. Our source code is available under https://github.com/rusty1s/ deep-graph-matching-consensus.","url_abs":"https://arxiv.org/abs/2001.09621v1","url_pdf":"https://arxiv.org/pdf/2001.09621v1.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":"deep-graph-matching-consensus-1","repo_url":"https://github.com/rusty1s/deep-graph-matching-consensus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-graph-matching-consensus-1","repo_url":"https://github.com/snap-stanford/neural-subgraph-learning-gnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"entity-alignment","task_name":"Entity Alignment"},{"task_slug":"graph-matching","task_name":"Graph Matching"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"re-ranking","task_name":"Re-Ranking"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/entity-alignment-on-dbp15k-zh-en","task":"Entity Alignment","dataset":"DBP15k zh-en","model":"Deep Graph Matching Consensus (L=10)","rank_in_archive_order":12,"of":38,"metrics":{"Hits@1":"0.8012"},"uses_additional_data":true},{"leaderboard":"/sota/entity-alignment-on-dbp15k-zh-en","task":"Entity Alignment","dataset":"DBP15k zh-en","model":"Deep Graph Matching Consensus","rank_in_archive_order":20,"of":38,"metrics":{"Hits@1":"0.7075"},"uses_additional_data":false},{"leaderboard":"/sota/entity-alignment-on-dbp15k-zh-en","task":"Entity Alignment","dataset":"DBP15k zh-en","model":"GMNN","rank_in_archive_order":23,"of":38,"metrics":{"Hits@1":"0.6793"},"uses_additional_data":true},{"leaderboard":"/sota/entity-alignment-on-dbp15k-zh-en","task":"Entity Alignment","dataset":"DBP15k zh-en","model":"NAEA","rank_in_archive_order":24,"of":38,"metrics":{"Hits@1":"0.6501"},"uses_additional_data":false},{"leaderboard":"/sota/entity-alignment-on-dbp15k-zh-en","task":"Entity Alignment","dataset":"DBP15k zh-en","model":"BootEA","rank_in_archive_order":26,"of":38,"metrics":{"Hits@1":"0.6294"},"uses_additional_data":false},{"leaderboard":"/sota/entity-alignment-on-dbp15k-zh-en","task":"Entity Alignment","dataset":"DBP15k zh-en","model":"MuGNN","rank_in_archive_order":30,"of":38,"metrics":{"Hits@1":"0.494"},"uses_additional_data":false},{"leaderboard":"/sota/entity-alignment-on-dbp15k-zh-en","task":"Entity Alignment","dataset":"DBP15k zh-en","model":"GCN-Align","rank_in_archive_order":35,"of":38,"metrics":{"Hits@1":"0.4125"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2001.09621","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}