{"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/edgnn-a-simple-and-powerful-gnn-for-directed","title":"edGNN: a Simple and Powerful GNN for Directed Labeled Graphs","arxiv_id":"1904.08745","date":"2019-04-18","proceeding":null,"authors":["Guillaume Jaume","An-phi Nguyen","María Rodríguez Martínez","Jean-Philippe Thiran","Maria Gabrani"],"abstract":"The ability of a graph neural network (GNN) to leverage both the graph topology and graph labels is fundamental to building discriminative node and graph embeddings. Building on previous work, we theoretically show that edGNN, our model for directed labeled graphs, is as powerful as the Weisfeiler-Lehman algorithm for graph isomorphism. Our experiments support our theoretical findings, confirming that graph neural networks can be used effectively for inference problems on directed graphs with both node and edge labels. Code available at https://github.com/guillaumejaume/edGNN.","url_abs":"https://arxiv.org/abs/1904.08745v2","url_pdf":"https://arxiv.org/pdf/1904.08745v2.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":"edgnn-a-simple-and-powerful-gnn-for-directed","repo_url":"https://github.com/guillaumejaume/edGNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-mutag","task":"Graph Classification","dataset":"MUTAG","model":"edGNN (max)","rank_in_archive_order":33,"of":74,"metrics":{"Accuracy":"88.8%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-mutag","task":"Graph Classification","dataset":"MUTAG","model":"edGNN (avg)","rank_in_archive_order":51,"of":74,"metrics":{"Accuracy":"86.9%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.08745","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}