{"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/beyond-homophily-structure-aware-path","title":"Beyond Homophily: Structure-aware Path Aggregation Graph Neural Network","arxiv_id":null,"date":"2022-07-20","proceeding":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence 2022 7","authors":["Yifei Sun","Haoran Deng","Yang Yang","Chunping Wang","Jiarong Xu","Renhong Huang","Linfeng Cao","Yang Wang","Lei Chen"],"abstract":"Graph neural networks (GNNs) have been intensively studied in various real-world tasks. However, the homophily assumption of GNNs' aggregation function limits their representation learning ability in heterophily graphs. In this paper, we shed light on the path level patterns in graphs that can explicitly reflect rich semantic and structural information. We therefore propose a novel Structure-aware Path Aggregation Graph Neural Network (PathNet) aiming to generalize GNNs for both homophily and heterophily graphs. Specifically, we first introduce a maximal entropy path sampler, which helps us sample a number of paths containing structural context. Then, we introduce a structure-aware recurrent cell consisting of order-preserving and distance-aware components to learn the semantic information of neighborhoods. Finally, we model the preference of different paths to target node after path encoding. Experimental results demonstrate that our model obtains significant improvements in node classification on both heterophily and homophily graphs.","url_abs":"https://www.ijcai.org/proceedings/2022/310","url_pdf":"http://yangy.org/works/gnn/IJCAI22_Beyond.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":"beyond-homophily-structure-aware-path","repo_url":"https://github.com/zjunet/PathNet","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"graph-mining","task_name":"Graph Mining"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[{"slug":"bgp","name":"BGP","full_name":"Border Gateway Protocol (BGP) Network"},{"slug":"electronics","name":"Electronics","full_name":""},{"slug":"nba","name":"NBA","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-bgp","task":"Node Classification","dataset":"BGP","model":"PathNet","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (%)":"65.71"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"PathNet","rank_in_archive_order":70,"of":71,"metrics":{"Accuracy (%)":"77.98"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"PathNet","rank_in_archive_order":60,"of":60,"metrics":{"Accuracy (%)":"91.35"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-electronics","task":"Node Classification","dataset":"Electronics","model":"PathNet","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (%)":"76.97"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-nba","task":"Node Classification","dataset":"NBA","model":"PathNet","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (%)":"71.69"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"PathNet","rank_in_archive_order":69,"of":70,"metrics":{"Accuracy (%)":"88.92"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}