{"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/orthogonal-relation-transforms-with-graph","title":"Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding","arxiv_id":"1911.04910","date":"2019-11-09","proceeding":"ACL 2020 6","authors":["Yun Tang","Jing Huang","Guangtao Wang","Xiaodong He","Bo-Wen Zhou"],"abstract":"Translational distance-based knowledge graph embedding has shown progressive improvements on the link prediction task, from TransE to the latest state-of-the-art RotatE. However, N-1, 1-N and N-N predictions still remain challenging. In this work, we propose a novel translational distance-based approach for knowledge graph link prediction. The proposed method includes two-folds, first we extend the RotatE from 2D complex domain to high dimension space with orthogonal transforms to model relations for better modeling capacity. Second, the graph context is explicitly modeled via two directed context representations. These context representations are used as part of the distance scoring function to measure the plausibility of the triples during training and inference. The proposed approach effectively improves prediction accuracy on the difficult N-1, 1-N and N-N cases for knowledge graph link prediction task. The experimental results show that it achieves better performance on two benchmark data sets compared to the baseline RotatE, especially on data set (FB15k-237) with many high in-degree connection nodes.","url_abs":"https://arxiv.org/abs/1911.04910v3","url_pdf":"https://arxiv.org/pdf/1911.04910v3.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":[],"tasks":[{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"knowledge-graph-embedding","task_name":"Knowledge Graph Embedding"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":null,"task_name":"Relation"}],"methods":[{"method_slug":"rotate","method_name":"RotatE"},{"method_slug":"self-adversarial-negative-sampling","method_name":"Self-Adversarial Negative Sampling"},{"method_slug":"transe","method_name":"TransE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-fb15k-237","task":"Link Prediction","dataset":"FB15k-237","model":"GC-OTE","rank_in_archive_order":19,"of":75,"metrics":{"Hits@1":"0.267","Hits@10":"0.550","Hits@3":"0.396","MR":"154","MRR":"0.361"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wn18rr","task":"Link Prediction","dataset":"WN18RR","model":"GC-OTE","rank_in_archive_order":22,"of":75,"metrics":{"Hits@1":"0.442","Hits@10":"0.583","Hits@3":"0.511","MR":"2715","MRR":"0.491"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.04910","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}