{"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/interht-knowledge-graph-embeddings-by","title":"InterHT: Knowledge Graph Embeddings by Interaction between Head and Tail Entities","arxiv_id":"2202.04897","date":"2022-02-10","proceeding":null,"authors":["Baoxin Wang","Qingye Meng","Ziyue Wang","Honghong Zhao","Dayong Wu","Wanxiang Che","Shijin Wang","Zhigang Chen","Cong Liu"],"abstract":"Knowledge graph embedding (KGE) models learn the representation of entities and relations in knowledge graphs. Distance-based methods show promising performance on link prediction task, which predicts the result by the distance between two entity representations. However, most of these methods represent the head entity and tail entity separately, which limits the model capacity. We propose two novel distance-based methods named InterHT and InterHT+ that allow the head and tail entities to interact better and get better entity representation. Experimental results show that our proposed method achieves the best results on ogbl-wikikg2 dataset.","url_abs":"https://arxiv.org/abs/2202.04897v2","url_pdf":"https://arxiv.org/pdf/2202.04897v2.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":"knowledge-graph-embeddings","task_name":"Knowledge Graph Embeddings"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"link-prediction","task_name":"Link Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-property-prediction-on-ogbl-wikikg2","task":"Link Property Prediction","dataset":"ogbl-wikikg2","model":"InterHT+","rank_in_archive_order":4,"of":30,"metrics":{"Ext. data":"No","Number of params":"156332770","Test MRR":"0.7293 ± 0.0018","Validation MRR":"0.7391 ± 0.0023"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-wikikg2","task":"Link Property Prediction","dataset":"ogbl-wikikg2","model":"InterHT+ (256dim)","rank_in_archive_order":5,"of":30,"metrics":{"Ext. data":"No","Number of params":"148000738","Test MRR":"0.7257 ± 0.0018","Validation MRR":"0.7370 ± 0.0022"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-wikikg2","task":"Link Property Prediction","dataset":"ogbl-wikikg2","model":"InterHT","rank_in_archive_order":9,"of":30,"metrics":{"Ext. data":"No","Number of params":"19215402","Test MRR":"0.6779 ± 0.0018","Validation MRR":"0.6893 ± 0.0015"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2202.04897","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}