{"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-topological-representation-for","title":"Learning Topological Representation for Networks via Hierarchical Sampling","arxiv_id":"1902.06684","date":"2019-02-15","proceeding":null,"authors":["Guoji Fu","Chengbin Hou","Xin Yao"],"abstract":"The topological information is essential for studying the relationship\nbetween nodes in a network. Recently, Network Representation Learning (NRL),\nwhich projects a network into a low-dimensional vector space, has been shown\ntheir advantages in analyzing large-scale networks. However, most existing NRL\nmethods are designed to preserve the local topology of a network, they fail to\ncapture the global topology. To tackle this issue, we propose a new NRL\nframework, named HSRL, to help existing NRL methods capture both the local and\nglobal topological information of a network. Specifically, HSRL recursively\ncompresses an input network into a series of smaller networks using a\ncommunity-awareness compressing strategy. Then, an existing NRL method is used\nto learn node embeddings for each compressed network. Finally, the node\nembeddings of the input network are obtained by concatenating the node\nembeddings from all compressed networks. Empirical studies for link prediction\non five real-world datasets demonstrate the advantages of HSRL over\nstate-of-the-art methods.","url_abs":"http://arxiv.org/abs/1902.06684v1","url_pdf":"http://arxiv.org/pdf/1902.06684v1.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-topological-representation-for","repo_url":"https://github.com/fuguoji/HSRL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-dblp","task":"Link Prediction","dataset":"DBLP","model":"HSRL (DW)","rank_in_archive_order":3,"of":3,"metrics":{"AUC":"84.7"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-douban","task":"Link Prediction","dataset":"Douban","model":"HSRL (DW)","rank_in_archive_order":1,"of":2,"metrics":{"AUC":"84.2"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-mit","task":"Link Prediction","dataset":"MIT","model":"HSRL (DW)","rank_in_archive_order":1,"of":1,"metrics":{"AUC":"92.6"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-yelp","task":"Link Prediction","dataset":"Yelp","model":"HSRL (DW)","rank_in_archive_order":8,"of":9,"metrics":{"AUC":"90.1"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}