{"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/sign-is-not-a-remedy-multiset-to-multiset","title":"Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs","arxiv_id":"2405.20652","date":"2024-05-31","proceeding":null,"authors":["Langzhang Liang","Sunwoo Kim","Kijung Shin","Zenglin Xu","Shirui Pan","Yuan Qi"],"abstract":"Graph Neural Networks (GNNs) have gained significant attention as a powerful modeling and inference method, especially for homophilic graph-structured data. To empower GNNs in heterophilic graphs, where adjacent nodes exhibit dissimilar labels or features, Signed Message Passing (SMP) has been widely adopted. However, there is a lack of theoretical and empirical analysis regarding the limitations of SMP. In this work, we unveil some potential pitfalls of SMP and their remedies. We first identify two limitations of SMP: undesirable representation update for multi-hop neighbors and vulnerability against oversmoothing issues. To overcome these challenges, we propose a novel message passing function called Multiset to Multiset GNN(M2M-GNN). Our theoretical analyses and extensive experiments demonstrate that M2M-GNN effectively alleviates the aforementioned limitations of SMP, yielding superior performance in comparison","url_abs":"https://arxiv.org/abs/2405.20652v1","url_pdf":"https://arxiv.org/pdf/2405.20652v1.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":"sign-is-not-a-remedy-multiset-to-multiset","repo_url":"https://github.com/Jinx-byebye/m2mgnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-actor","task":"Node Classification","dataset":"Actor","model":"M2M-GNN","rank_in_archive_order":32,"of":62,"metrics":{"Accuracy":"36.72 ± 1.6"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"M2M-GNN","rank_in_archive_order":10,"of":61,"metrics":{"Accuracy":"75.20 ± 2.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"M2M-GNN","rank_in_archive_order":11,"of":60,"metrics":{"Accuracy":"86.48 ± 6.1"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel","task":"Node Classification","dataset":"Squirrel","model":"M2M-GNN","rank_in_archive_order":19,"of":59,"metrics":{"Accuracy":"63.60 ± 1.7"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset":"Texas","model":"M2M-GNN","rank_in_archive_order":6,"of":62,"metrics":{"Accuracy":"89.19 ± 4.5"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset":"Wisconsin","model":"M2M-GNN","rank_in_archive_order":7,"of":63,"metrics":{"Accuracy":"89.01 ± 4.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.20652","atlas_url":"https://app.syntology.ai/?focus=2405.20652","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}