{"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-role-based-graph-embeddings","title":"Learning Role-based Graph Embeddings","arxiv_id":"1802.02896","date":"2018-02-07","proceeding":"IJCAI 2018 7","authors":["Nesreen K. Ahmed","Ryan Rossi","John Boaz Lee","Theodore L. Willke","Rong Zhou","Xiangnan Kong","Hoda Eldardiry"],"abstract":"Random walks are at the heart of many existing network embedding methods.\nHowever, such algorithms have many limitations that arise from the use of\nrandom walks, e.g., the features resulting from these methods are unable to\ntransfer to new nodes and graphs as they are tied to vertex identity. In this\nwork, we introduce the Role2Vec framework which uses the flexible notion of\nattributed random walks, and serves as a basis for generalizing existing\nmethods such as DeepWalk, node2vec, and many others that leverage random walks.\nOur proposed framework enables these methods to be more widely applicable for\nboth transductive and inductive learning as well as for use on graphs with\nattributes (if available). This is achieved by learning functions that\ngeneralize to new nodes and graphs. We show that our proposed framework is\neffective with an average AUC improvement of 16.55% while requiring on average\n853x less space than existing methods on a variety of graphs.","url_abs":"http://arxiv.org/abs/1802.02896v2","url_pdf":"http://arxiv.org/pdf/1802.02896v2.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-role-based-graph-embeddings","repo_url":"https://github.com/benedekrozemberczki/karateclub","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"learning-role-based-graph-embeddings","repo_url":"https://github.com/benedekrozemberczki/role2vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"inductive-learning","task_name":"Inductive Learning"},{"task_slug":"network-embedding","task_name":"Network Embedding"}],"methods":[{"method_slug":"deepwalk","method_name":"DeepWalk"},{"method_slug":"node2vec","method_name":"node2vec"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.02896","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}