{"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/unsupervised-network-embedding-for-graph","title":"Unsupervised Network Embedding for Graph Visualization, Clustering and Classification","arxiv_id":"1903.05980","date":"2019-02-25","proceeding":null,"authors":["Leonardo Gutiérrez-Gómez","Jean-Charles Delvenne"],"abstract":"A main challenge in mining network-based data is finding effective ways to\nrepresent or encode graph structures so that it can be efficiently exploited by\nmachine learning algorithms. Several methods have focused in network\nrepresentation at node/edge or substructure level. However, many real life\nchallenges such as time-varying, multilayer, chemical compounds and brain\nnetworks involve analysis of a family of graphs instead of single one opening\nadditional challenges in graph comparison and representation. Traditional\napproaches for learning representations relies on hand-crafting specialized\nheuristics to extract meaningful information about the graphs, e.g statistical\nproperties, structural features, etc. as well as engineered graph distances to\nquantify dissimilarity between networks. In this work we provide an\nunsupervised approach to learn embedding representation for a collection of\ngraphs so that it can be used in numerous graph mining tasks. By using an\nunsupervised neural network approach on input graphs, we aim to capture the\nunderlying distribution of the data in order to discriminate between different\nclass of networks. Our method is assessed empirically on synthetic and real\nlife datasets and evaluated in three different tasks: graph clustering,\nvisualization and classification. Results reveal that our method outperforms\nwell known graph distances and graph-kernels in clustering and classification\ntasks, being highly efficient in runtime.","url_abs":"http://arxiv.org/abs/1903.05980v2","url_pdf":"http://arxiv.org/pdf/1903.05980v2.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":"unsupervised-network-embedding-for-graph","repo_url":"https://github.com/leoguti85/GraphEmbs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"graph-clustering","task_name":"Graph Clustering"},{"task_slug":"graph-mining","task_name":"Graph Mining"},{"task_slug":"network-embedding","task_name":"Network Embedding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}