{"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/rot-pro-modeling-transitivity-by-projection","title":"Rot-Pro: Modeling Transitivity by Projection in Knowledge Graph Embedding","arxiv_id":"2110.14450","date":"2021-10-27","proceeding":"NeurIPS 2021 12","authors":["Tengwei Song","Jie Luo","Lei Huang"],"abstract":"Knowledge graph embedding models learn the representations of entities and relations in the knowledge graphs for predicting missing links (relations) between entities. Their effectiveness are deeply affected by the ability of modeling and inferring different relation patterns such as symmetry, asymmetry, inversion, composition and transitivity. Although existing models are already able to model many of these relations patterns, transitivity, a very common relation pattern, is still not been fully supported. In this paper, we first theoretically show that the transitive relations can be modeled with projections. We then propose the Rot-Pro model which combines the projection and relational rotation together. We prove that Rot-Pro can infer all the above relation patterns. Experimental results show that the proposed Rot-Pro model effectively learns the transitivity pattern and achieves the state-of-the-art results on the link prediction task in the datasets containing transitive relations.","url_abs":"https://arxiv.org/abs/2110.14450v1","url_pdf":"https://arxiv.org/pdf/2110.14450v1.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":"rot-pro-modeling-transitivity-by-projection","repo_url":"https://github.com/tewiSong/Rot-Pro","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"rot-pro-modeling-transitivity-by-projection","repo_url":"https://github.com/Tigter/ogblwikikg2-RotPro","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"knowledge-graph-embedding","task_name":"Knowledge Graph Embedding"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":null,"task_name":"Relation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-fb15k-237","task":"Link Prediction","dataset":"FB15k-237","model":"Rot-Pro","rank_in_archive_order":41,"of":75,"metrics":{"Hits@1":"0.246","Hits@10":"0.540","Hits@3":"0.383","MRR":"0.344"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wn18rr","task":"Link Prediction","dataset":"WN18RR","model":"Rot-Pro","rank_in_archive_order":32,"of":75,"metrics":{"Hits@1":"0.397","Hits@10":"0.577","Hits@3":"0.482","MRR":"0.457"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-yago3-10","task":"Link Prediction","dataset":"YAGO3-10","model":"Rot-Pro","rank_in_archive_order":13,"of":18,"metrics":{"Hits@1":"0.443","Hits@10":"0.699","Hits@3":"0.596","MRR":"0.542"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-wikikg2","task":"Link Property Prediction","dataset":"ogbl-wikikg2","model":"Rot-Pro","rank_in_archive_order":19,"of":30,"metrics":{"Ext. data":"No","Number of params":"1000669602","Test MRR":"0.5602 ± 0.0016","Validation MRR":"0.5740 ± 0.0008"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-wikikg2","task":"Link Property Prediction","dataset":"ogbl-wikikg2","model":"RotPro","rank_in_archive_order":23,"of":30,"metrics":{"Ext. data":"No","Number of params":"1000669602","Test MRR":"0.4277 ± 0.0008","Validation MRR":"0.4174 ± 0.0058"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.14450","atlas_url":"https://app.syntology.ai/?focus=2110.14450","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}