{"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/knowledge-graph-embedding-with-iterative","title":"Knowledge Graph Embedding with Iterative Guidance from Soft Rules","arxiv_id":"1711.11231","date":"2017-11-30","proceeding":null,"authors":["Shu Guo","Quan Wang","Lihong Wang","Bin Wang","Li Guo"],"abstract":"Embedding knowledge graphs (KGs) into continuous vector spaces is a focus of\ncurrent research. Combining such an embedding model with logic rules has\nrecently attracted increasing attention. Most previous attempts made a one-time\ninjection of logic rules, ignoring the interactive nature between embedding\nlearning and logical inference. And they focused only on hard rules, which\nalways hold with no exception and usually require extensive manual effort to\ncreate or validate. In this paper, we propose Rule-Guided Embedding (RUGE), a\nnovel paradigm of KG embedding with iterative guidance from soft rules. RUGE\nenables an embedding model to learn simultaneously from 1) labeled triples that\nhave been directly observed in a given KG, 2) unlabeled triples whose labels\nare going to be predicted iteratively, and 3) soft rules with various\nconfidence levels extracted automatically from the KG. In the learning process,\nRUGE iteratively queries rules to obtain soft labels for unlabeled triples, and\nintegrates such newly labeled triples to update the embedding model. Through\nthis iterative procedure, knowledge embodied in logic rules may be better\ntransferred into the learned embeddings. We evaluate RUGE in link prediction on\nFreebase and YAGO. Experimental results show that: 1) with rule knowledge\ninjected iteratively, RUGE achieves significant and consistent improvements\nover state-of-the-art baselines; and 2) despite their uncertainties,\nautomatically extracted soft rules are highly beneficial to KG embedding, even\nthose with moderate confidence levels. The code and data used for this paper\ncan be obtained from https://github.com/iieir-km/RUGE.","url_abs":"http://arxiv.org/abs/1711.11231v1","url_pdf":"http://arxiv.org/pdf/1711.11231v1.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":"knowledge-graph-embedding-with-iterative","repo_url":"https://github.com/iieir-km/RUGE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-fb15k-1","task":"Link Prediction","dataset":"FB15k","model":"Rule-Guided Embedding","rank_in_archive_order":7,"of":10,"metrics":{"Hits@1":"0.703","Hits@10":"0.865","Hits@3":"0.815","Hits@5":"0.836","MRR":"0.768"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-yago37","task":"Link Prediction","dataset":"YAGO37","model":"Rule-Guided Embedding","rank_in_archive_order":2,"of":2,"metrics":{"Hits@1":"0.34","Hits@10":"0.603","Hits@3":"0.482","Hits@5":"0.541","MRR":"0.431"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.11231","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}