{"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/learning-convolutional-neural-networks-for","title":"Learning Convolutional Neural Networks for Graphs","arxiv_id":"1605.05273","date":"2016-05-17","proceeding":null,"authors":["Mathias Niepert","Mohamed Ahmed","Konstantin Kutzkov"],"abstract":"Numerous important problems can be framed as learning from graph data. We\npropose a framework for learning convolutional neural networks for arbitrary\ngraphs. These graphs may be undirected, directed, and with both discrete and\ncontinuous node and edge attributes. Analogous to image-based convolutional\nnetworks that operate on locally connected regions of the input, we present a\ngeneral approach to extracting locally connected regions from graphs. Using\nestablished benchmark data sets, we demonstrate that the learned feature\nrepresentations are competitive with state of the art graph kernels and that\ntheir computation is highly efficient.","url_abs":"http://arxiv.org/abs/1605.05273v4","url_pdf":"http://arxiv.org/pdf/1605.05273v4.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":"learning-convolutional-neural-networks-for","repo_url":"https://github.com/CielAl/PatchySan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"learning-convolutional-neural-networks-for","repo_url":"https://github.com/tvayer/PSCN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-cox2","task":"Graph Classification","dataset":"COX2","model":"PSCN","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy(10-fold)":"75.21"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-dd","task":"Graph Classification","dataset":"D&D","model":"PSCN","rank_in_archive_order":38,"of":53,"metrics":{"Accuracy":"76.27%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-b","task":"Graph Classification","dataset":"IMDb-B","model":"PSCN","rank_in_archive_order":44,"of":51,"metrics":{"Accuracy":"71.00%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-mutag","task":"Graph Classification","dataset":"MUTAG","model":"PATCHY-SAN","rank_in_archive_order":12,"of":74,"metrics":{"Accuracy":"92.63%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-mutag","task":"Graph Classification","dataset":"MUTAG","model":"PSCN","rank_in_archive_order":31,"of":74,"metrics":{"Accuracy":"88.95%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci1","task":"Graph Classification","dataset":"NCI1","model":"PSCN","rank_in_archive_order":48,"of":69,"metrics":{"Accuracy":"76.34%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-ptc","task":"Graph Classification","dataset":"PTC","model":"PATCHY-SAN","rank_in_archive_order":34,"of":37,"metrics":{"Accuracy":"60.00%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1605.05273","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}