{"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/translating-embeddings-for-modeling-multi","title":"Translating Embeddings for Modeling Multi-relational Data","arxiv_id":null,"date":"2013-12-01","proceeding":"NeurIPS 2013 12","authors":["Antoine Bordes","Nicolas Usunier","Alberto Garcia-Duran","Jason Weston","Oksana Yakhnenko"],"abstract":"We consider the problem of embedding entities and relationships of multi-relational data in low-dimensional vector spaces. Our objective is to propose a canonical model which is easy to train, contains a reduced number of parameters and can scale up to very large databases. Hence, we propose, TransE, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities. Despite its simplicity, this assumption proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases. Besides, it can be successfully trained on a large scale data set with 1M entities, 25k relationships and more than 17M training samples.","url_abs":"http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data","url_pdf":"http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.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":"translating-embeddings-for-modeling-multi","repo_url":"https://github.com/2023-MindSpore-1/ms-code-220/tree/main/transX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"translating-embeddings-for-modeling-multi","repo_url":"https://github.com/Accenture/AmpliGraph","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"translating-embeddings-for-modeling-multi","repo_url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/transX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"translating-embeddings-for-modeling-multi","repo_url":"https://github.com/bi-graph/emgraph","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"translating-embeddings-for-modeling-multi","repo_url":"https://github.com/pyg-team/pytorch_geometric/blob/master/torch_geometric/nn/kge/transe.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"translating-embeddings-for-modeling-multi","repo_url":"https://github.com/wrk226/Translating-Embeddings-for-Modeling-Multi-relational-Data","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"translating-embeddings-for-modeling-multi","repo_url":"https://github.com/yangyucheng000/TransX-2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"translating-embeddings-for-modeling-multi","repo_url":"https://github.com/yangyucheng000/transX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"}],"methods":[{"method_slug":"transe","method_name":"TransE"}],"datasets_introduced":[{"slug":"fb15k","name":"FB15k","full_name":"Freebase 15K"},{"slug":"wn18","name":"WN18","full_name":"WordNet18"},{"slug":"wn18rr","name":"WN18RR","full_name":""}],"methods_introduced":[{"slug":"transe","name":"TransE","full_name":"TransE"}],"results":[{"leaderboard":"/sota/link-prediction-on-fb122","task":"Link Prediction","dataset":"FB122","model":"TransE","rank_in_archive_order":5,"of":5,"metrics":{"HITS@3":"58.9","Hits@10":"70.2","Hits@5":"64.2","MRR":"48.0"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-fb15k","task":"Link Prediction","dataset":"FB15k","model":"TransE","rank_in_archive_order":23,"of":23,"metrics":{"Hits@10":"0.471","MR":"125"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-fb15k-237","task":"Link Prediction","dataset":"FB15k-237","model":"TransE","rank_in_archive_order":51,"of":75,"metrics":{"Hits@1":"0.1987","Hits@10":".4709","MRR":"0.2904"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-umls","task":"Link Prediction","dataset":"UMLS","model":"TransE","rank_in_archive_order":8,"of":10,"metrics":{"Hits@10":"0.989","MR":"1.84"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wn18","task":"Link Prediction","dataset":"WN18","model":"TransE","rank_in_archive_order":32,"of":37,"metrics":{"Hits@10":"0.754","MR":"263"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wn18rr","task":"Link Prediction","dataset":"WN18RR","model":"TransE","rank_in_archive_order":48,"of":75,"metrics":{"Hits@1":"0.4226","Hits@10":"0.5555","MRR":"0.4659"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}