{"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/reasoning-through-memorization-nearest","title":"Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings","arxiv_id":"2201.05575","date":"2022-01-14","proceeding":null,"authors":["Peng Wang","Xin Xie","Xiaohan Wang","Ningyu Zhang"],"abstract":"Previous knowledge graph embedding approaches usually map entities to representations and utilize score functions to predict the target entities, yet they typically struggle to reason rare or emerging unseen entities. In this paper, we propose kNN-KGE, a new knowledge graph embedding approach with pre-trained language models, by linearly interpolating its entity distribution with k-nearest neighbors. We compute the nearest neighbors based on the distance in the entity embedding space from the knowledge store. Our approach can allow rare or emerging entities to be memorized explicitly rather than implicitly in model parameters. Experimental results demonstrate that our approach can improve inductive and transductive link prediction results and yield better performance for low-resource settings with only a few triples, which might be easier to reason via explicit memory. Code is available at https://github.com/zjunlp/KNN-KG.","url_abs":"https://arxiv.org/abs/2201.05575v4","url_pdf":"https://arxiv.org/pdf/2201.05575v4.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":"reasoning-through-memorization-nearest","repo_url":"https://github.com/zjunlp/knn-kg","is_official":1,"mentioned_in_paper":1,"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-graph-embeddings","task_name":"Knowledge Graph Embeddings"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"memorization","task_name":"Memorization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-fb15k-237","task":"Link Prediction","dataset":"FB15k-237","model":"kNN-KGE","rank_in_archive_order":9,"of":75,"metrics":{"Hits@1":"0.280","Hits@10":"0.550","Hits@3":"0.404","MR":"185","MRR":"0.370"},"uses_additional_data":true},{"leaderboard":"/sota/link-prediction-on-fb15k-237-ind","task":"Link Prediction","dataset":"FB15k-237-ind","model":"kNN-KGE","rank_in_archive_order":1,"of":1,"metrics":{"Hits@1":"0.223","Hits@10":"0.431","Hits@3":"0.32","MRR":"0.294"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.05575","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}