{"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/representation-learning-for-heterogeneous","title":"Representation Learning for Heterogeneous Information Networks via Embedding Events","arxiv_id":"1901.10234","date":"2019-01-29","proceeding":null,"authors":["Guoji Fu","Bo Yuan","Qiqi Duan","Xin Yao"],"abstract":"Network representation learning (NRL) has been widely used to help analyze\nlarge-scale networks through mapping original networks into a low-dimensional\nvector space. However, existing NRL methods ignore the impact of properties of\nrelations on the object relevance in heterogeneous information networks (HINs).\nTo tackle this issue, this paper proposes a new NRL framework, called\nEvent2vec, for HINs to consider both quantities and properties of relations\nduring the representation learning process. Specifically, an event (i.e., a\ncomplete semantic unit) is used to represent the relation among multiple\nobjects, and both event-driven first-order and second-order proximities are\ndefined to measure the object relevance according to the quantities and\nproperties of relations. We theoretically prove how event-driven proximities\ncan be preserved in the embedding space by Event2vec, which utilizes event\nembeddings to facilitate learning the object embeddings. Experimental studies\ndemonstrate the advantages of Event2vec over state-of-the-art algorithms on\nfour real-world datasets and three network analysis tasks (including network\nreconstruction, link prediction, and node classification).","url_abs":"http://arxiv.org/abs/1901.10234v2","url_pdf":"http://arxiv.org/pdf/1901.10234v2.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":"representation-learning-for-heterogeneous","repo_url":"https://github.com/fuguoji/Event2vec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"object","task_name":"Object"},{"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":"Event2vec","rank_in_archive_order":2,"of":3,"metrics":{"AUC":"90.1"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-douban","task":"Link Prediction","dataset":"Douban","model":"Event2vec","rank_in_archive_order":2,"of":2,"metrics":{"AUC":"82.3"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-imdb","task":"Link Prediction","dataset":"IMDb","model":"Event2vec","rank_in_archive_order":1,"of":1,"metrics":{"AUC":"89.4"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-yelp","task":"Link Prediction","dataset":"Yelp","model":"Event2vec","rank_in_archive_order":9,"of":9,"metrics":{"AUC":"86.2"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}