{"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/relation-aware-ensemble-learning-for","title":"Relation-aware Ensemble Learning for Knowledge Graph Embedding","arxiv_id":"2310.08917","date":"2023-10-13","proceeding":null,"authors":["Ling Yue","Yongqi Zhang","Quanming Yao","Yong Li","Xian Wu","Ziheng Zhang","Zhenxi Lin","Yefeng Zheng"],"abstract":"Knowledge graph (KG) embedding is a fundamental task in natural language processing, and various methods have been proposed to explore semantic patterns in distinctive ways. In this paper, we propose to learn an ensemble by leveraging existing methods in a relation-aware manner. However, exploring these semantics using relation-aware ensemble leads to a much larger search space than general ensemble methods. To address this issue, we propose a divide-search-combine algorithm RelEns-DSC that searches the relation-wise ensemble weights independently. This algorithm has the same computation cost as general ensemble methods but with much better performance. Experimental results on benchmark datasets demonstrate the effectiveness of the proposed method in efficiently searching relation-aware ensemble weights and achieving state-of-the-art embedding performance. The code is public at https://github.com/LARS-research/RelEns.","url_abs":"https://arxiv.org/abs/2310.08917v1","url_pdf":"https://arxiv.org/pdf/2310.08917v1.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":"relation-aware-ensemble-learning-for","repo_url":"https://github.com/lars-research/relens","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"relation-aware-ensemble-learning-for","repo_url":"https://github.com/LARS-research/RelEns","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"ensemble-learning","task_name":"Ensemble Learning"},{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"knowledge-graph-embedding","task_name":"Knowledge Graph Embedding"},{"task_slug":null,"task_name":"Relation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-property-prediction-on-ogbl-biokg","task":"Link Property Prediction","dataset":"ogbl-biokg","model":"RelEns","rank_in_archive_order":1,"of":16,"metrics":{"Ext. data":"No","Number of params":"849427106","Test MRR":"0.9618 ± 0.0002","Validation MRR":"0.9627 ± 0.0004"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-wikikg2","task":"Link Property Prediction","dataset":"ogbl-wikikg2","model":"RelEns","rank_in_archive_order":1,"of":30,"metrics":{"Ext. data":"No","Number of params":"2176767622","Test MRR":"0.7392 ± 0.0011","Validation MRR":"0.7509 ± 0.0009"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.08917","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}