{"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/multi-hop-attention-based-graph-pooling-a","title":"Multi-hop Attention-based Graph Pooling: A Personalized PageRank Perspective","arxiv_id":null,"date":"2024-03-04","proceeding":"International Conference on Distributed Computing and High Performance Computing (DCHPC) 2024 3","authors":["Parsa Haddadian","Roya Booryaee","Rooholah Abedian","Ali Moeini"],"abstract":"Over the past ten years, graph representation learning has garnered a lot of attention due to the variety of graph-structured data and its efficiency in both time and space. One essential method for obtaining effective graph representations is graph pooling. Numerous studies on the graph pooling technique have been conducted. Cutting-edge results on a range of graph representation learning tasks were made possible by the combination of graph neural networks and self-attention mechanisms. Nevertheless, the attention mechanism has limitations since it ignores nodes that have no direct connection via an edge but provide valuable network context information. This paper proposes a graph pooling approach based on Personalized PageRank and self-attention, which improves the model to take into account both node properties and graph structure. The experimental findings indicate that, with a suitable number of parameters, the MAGPool approach delivers greater accuracy on the benchmark datasets.","url_abs":"https://ieeexplore.ieee.org/document/10454077","url_pdf":"https://ieeexplore.ieee.org/document/10454077","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":"multi-hop-attention-based-graph-pooling-a","repo_url":"https://github.com/p-haddadian/MAGPool","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-representation-learning","task_name":"Graph Representation Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-dd","task":"Graph Classification","dataset":"D&D","model":"MAGPool","rank_in_archive_order":15,"of":53,"metrics":{"Accuracy":"79.83%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-frankenstein","task":"Graph Classification","dataset":"FRANKENSTEIN","model":"MAGPool","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy":"67.21"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci1","task":"Graph Classification","dataset":"NCI1","model":"MAGPool","rank_in_archive_order":60,"of":69,"metrics":{"Accuracy":"72.32%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci109","task":"Graph Classification","dataset":"NCI109","model":"MAGPool","rank_in_archive_order":32,"of":38,"metrics":{"Accuracy":"73.43%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-proteins","task":"Graph Classification","dataset":"PROTEINS","model":"MAGPool","rank_in_archive_order":10,"of":103,"metrics":{"Accuracy":"80.36%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}