{"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/gemsec-graph-embedding-with-self-clustering","title":"GEMSEC: Graph Embedding with Self Clustering","arxiv_id":"1802.03997","date":"2018-02-12","proceeding":null,"authors":["Benedek Rozemberczki","Ryan Davies","Rik Sarkar","Charles Sutton"],"abstract":"Modern graph embedding procedures can efficiently process graphs with millions of nodes. In this paper, we propose GEMSEC -- a graph embedding algorithm which learns a clustering of the nodes simultaneously with computing their embedding. GEMSEC is a general extension of earlier work in the domain of sequence-based graph embedding. GEMSEC places nodes in an abstract feature space where the vertex features minimize the negative log-likelihood of preserving sampled vertex neighborhoods, and it incorporates known social network properties through a machine learning regularization. We present two new social network datasets and show that by simultaneously considering the embedding and clustering problems with respect to social properties, GEMSEC extracts high-quality clusters competitive with or superior to other community detection algorithms. In experiments, the method is found to be computationally efficient and robust to the choice of hyperparameters.","url_abs":"http://arxiv.org/abs/1802.03997v1","url_pdf":"http://arxiv.org/pdf/1802.03997v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"gemsec-graph-embedding-with-self-clustering","repo_url":"https://github.com/benedekrozemberczki/GEMSEC","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"gemsec-graph-embedding-with-self-clustering","repo_url":"https://github.com/benedekrozemberczki/GRAF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"gemsec-graph-embedding-with-self-clustering","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"}}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"deezer-user-networks","name":"Deezer User Networks","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/community-detection-on-facebook-artists","task":"Community Detection","dataset":"Facebook Artists","model":"Smooth GEMSEC 2","rank_in_archive_order":1,"of":1,"metrics":{"Modularity":"0.562"},"uses_additional_data":false},{"leaderboard":"/sota/community-detection-on-facebook-athletes","task":"Community Detection","dataset":"Facebook Athletes","model":"Smooth GEMSEC 2","rank_in_archive_order":1,"of":1,"metrics":{"Modularity":"0.692"},"uses_additional_data":false},{"leaderboard":"/sota/community-detection-on-facebook-celebrities","task":"Community Detection","dataset":"Facebook Celebrities","model":"Smooth GEMSEC 2","rank_in_archive_order":1,"of":1,"metrics":{"Modularity":"0.649"},"uses_additional_data":false},{"leaderboard":"/sota/community-detection-on-facebook-companies","task":"Community Detection","dataset":"Facebook Companies","model":"Smooth GEMSEC 2","rank_in_archive_order":1,"of":1,"metrics":{"Modularity":"0.684"},"uses_additional_data":false},{"leaderboard":"/sota/community-detection-on-facebook-government","task":"Community Detection","dataset":"Facebook Government","model":"Smooth GEMSEC 2","rank_in_archive_order":1,"of":1,"metrics":{"Modularity":"0.712"},"uses_additional_data":false},{"leaderboard":"/sota/community-detection-on-facebook-media","task":"Community Detection","dataset":"Facebook Media","model":"Smooth GEMSEC 2","rank_in_archive_order":1,"of":1,"metrics":{"Modularity":"0.571"},"uses_additional_data":false},{"leaderboard":"/sota/community-detection-on-facebook-politicians","task":"Community Detection","dataset":"Facebook Politicians","model":"Smooth GEMSEC 2","rank_in_archive_order":1,"of":1,"metrics":{"Modularity":"0.859"},"uses_additional_data":false},{"leaderboard":"/sota/community-detection-on-facebook-tv-show","task":"Community Detection","dataset":"Facebook TV Show","model":"Smooth GEMSEC 2","rank_in_archive_order":1,"of":1,"metrics":{"Modularity":"0.847"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-deezer-croatia","task":"Node Classification","dataset":"Deezer Croatia","model":"GEMSEC 2","rank_in_archive_order":1,"of":1,"metrics":{"Micro-F1":"0.381"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-deezer-hungary","task":"Node Classification","dataset":"Deezer Hungary","model":"Smooth GEMSEC 2","rank_in_archive_order":1,"of":1,"metrics":{"Micro-F1":"0.409"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-deezer-romania","task":"Node Classification","dataset":"Deezer Romania","model":"GEMSEC 2","rank_in_archive_order":2,"of":2,"metrics":{"Micro-F1":"0.378"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.03997","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}