{"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/graph-embedding-techniques-applications-and","title":"Graph Embedding Techniques, Applications, and Performance: A Survey","arxiv_id":"1705.02801","date":"2017-05-08","proceeding":null,"authors":["Palash Goyal","Emilio Ferrara"],"abstract":"Graphs, such as social networks, word co-occurrence networks, and\ncommunication networks, occur naturally in various real-world applications.\nAnalyzing them yields insight into the structure of society, language, and\ndifferent patterns of communication. Many approaches have been proposed to\nperform the analysis. Recently, methods which use the representation of graph\nnodes in vector space have gained traction from the research community. In this\nsurvey, we provide a comprehensive and structured analysis of various graph\nembedding techniques proposed in the literature. We first introduce the\nembedding task and its challenges such as scalability, choice of\ndimensionality, and features to be preserved, and their possible solutions. We\nthen present three categories of approaches based on factorization methods,\nrandom walks, and deep learning, with examples of representative algorithms in\neach category and analysis of their performance on various tasks. We evaluate\nthese state-of-the-art methods on a few common datasets and compare their\nperformance against one another. Our analysis concludes by suggesting some\npotential applications and future directions. We finally present the\nopen-source Python library we developed, named GEM (Graph Embedding Methods,\navailable at https://github.com/palash1992/GEM), which provides all presented\nalgorithms within a unified interface to foster and facilitate research on the\ntopic.","url_abs":"http://arxiv.org/abs/1705.02801v4","url_pdf":"http://arxiv.org/pdf/1705.02801v4.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":"graph-embedding-techniques-applications-and","repo_url":"https://github.com/palash1992/GEM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"graph-embedding-techniques-applications-and","repo_url":"https://github.com/agoodweathercc/EmbeddingEval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"graph-embedding-techniques-applications-and","repo_url":"https://github.com/olekscode/Power2TheWiki","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"survey","task_name":"Survey"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.02801","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}