{"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/friendly-neighbors-contextualized-sequence-to","title":"Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction","arxiv_id":"2305.13059","date":"2023-05-22","proceeding":null,"authors":["Adrian Kochsiek","Apoorv Saxena","Inderjeet Nair","Rainer Gemulla"],"abstract":"We propose KGT5-context, a simple sequence-to-sequence model for link prediction (LP) in knowledge graphs (KG). Our work expands on KGT5, a recent LP model that exploits textual features of the KG, has small model size, and is scalable. To reach good predictive performance, however, KGT5 relies on an ensemble with a knowledge graph embedding model, which itself is excessively large and costly to use. In this short paper, we show empirically that adding contextual information - i.e., information about the direct neighborhood of the query entity - alleviates the need for a separate KGE model to obtain good performance. The resulting KGT5-context model is simple, reduces model size significantly, and obtains state-of-the-art performance in our experimental study.","url_abs":"https://arxiv.org/abs/2305.13059v2","url_pdf":"https://arxiv.org/pdf/2305.13059v2.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":"friendly-neighbors-contextualized-sequence-to","repo_url":"https://github.com/uma-pi1/kgt5-context","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"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":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-wikidata5m","task":"Link Prediction","dataset":"Wikidata5M","model":"KGT5-context + Description","rank_in_archive_order":2,"of":14,"metrics":{"Hits@1":"0.406","Hits@10":"0.46","Hits@3":"0.44","MRR":"0.426"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wikidata5m","task":"Link Prediction","dataset":"Wikidata5M","model":"KGT5 + Description","rank_in_archive_order":3,"of":14,"metrics":{"Hits@1":"0.357","Hits@10":"0.422","Hits@3":"0.397","MRR":"0.381"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wikidata5m","task":"Link Prediction","dataset":"Wikidata5M","model":"KGT5-context","rank_in_archive_order":4,"of":14,"metrics":{"Hits@1":"0.35","Hits@10":"0.427","Hits@3":"0.396","MRR":"0.378"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.13059","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}