{"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/deeppath-a-reinforcement-learning-method-for","title":"DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning","arxiv_id":"1707.06690","date":"2017-07-20","proceeding":"EMNLP 2017 9","authors":["Wenhan Xiong","Thien Hoang","William Yang Wang"],"abstract":"We study the problem of learning to reason in large scale knowledge graphs\n(KGs). More specifically, we describe a novel reinforcement learning framework\nfor learning multi-hop relational paths: we use a policy-based agent with\ncontinuous states based on knowledge graph embeddings, which reasons in a KG\nvector space by sampling the most promising relation to extend its path. In\ncontrast to prior work, our approach includes a reward function that takes the\naccuracy, diversity, and efficiency into consideration. Experimentally, we show\nthat our proposed method outperforms a path-ranking based algorithm and\nknowledge graph embedding methods on Freebase and Never-Ending Language\nLearning datasets.","url_abs":"http://arxiv.org/abs/1707.06690v3","url_pdf":"http://arxiv.org/pdf/1707.06690v3.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":"deeppath-a-reinforcement-learning-method-for","repo_url":"https://github.com/xwhan/DeepPath","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"deeppath-a-reinforcement-learning-method-for","repo_url":"https://github.com/adymaharana/DeepPath_PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"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":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[{"slug":"nell-995","name":"NELL-995","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-nell-995","task":"Link Prediction","dataset":"NELL-995","model":"RL","rank_in_archive_order":4,"of":4,"metrics":{"Mean AP":"79.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.06690","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}