{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,29]],"date-time":"2026-03-29T08:46:55Z","timestamp":1774774015429,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2059"],"award-info":[{"award-number":["U22B2059"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276083"],"award-info":[{"award-number":["62276083"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Heilongjiang Providence","award":["2022ZX01A28"],"award-info":[{"award-number":["2022ZX01A28"]}]},{"name":"5G Application Innovation Joint Research Institute's","award":["A003"],"award-info":[{"award-number":["A003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tkde.2025.3631495","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T18:29:31Z","timestamp":1762885771000},"page":"1319-1333","source":"Crossref","is-referenced-by-count":1,"title":["Subgraph-Centric Multi-Agent Reinforcement Learning for Multi-Hop Knowledge Graph Reasoning"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6052-4573","authenticated-orcid":false,"given":"Tao","family":"He","sequence":"first","affiliation":[{"name":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, Heilongjiang, China"}]},{"given":"Zerui","family":"Chen","sequence":"additional","affiliation":[{"name":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, Heilongjiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9973-3305","authenticated-orcid":false,"given":"Lizi","family":"Liao","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore"}]},{"given":"Yixin","family":"Cao","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"given":"Yuanxing","family":"Liu","sequence":"additional","affiliation":[{"name":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, Heilongjiang, China"}]},{"given":"Wei","family":"Tang","sequence":"additional","affiliation":[{"name":"State Grid Anhui Electric Power Research Institute, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7163-9560","authenticated-orcid":false,"given":"Xun","family":"Mao","sequence":"additional","affiliation":[{"name":"State Grid Anhui Electric Power Research Institute, Hefei, China"}]},{"given":"Kai","family":"Lv","sequence":"additional","affiliation":[{"name":"State Grid Anhui Electric Power Research Institute, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7915-1001","authenticated-orcid":false,"given":"Ming","family":"Liu","sequence":"additional","affiliation":[{"name":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, Heilongjiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2543-5604","authenticated-orcid":false,"given":"Bing","family":"Qin","sequence":"additional","affiliation":[{"name":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, Heilongjiang, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2014.6816754"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403092"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3309547"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3579051.3579058"},{"key":"ref5","article-title":"Composition-based multi-relational graph convolutional networks","author":"Vashishth","year":"2019"},{"key":"ref6","first-page":"3243","article-title":"Multi-hop knowledge graph reasoning with reward shaping","volume-title":"Proc. 2018 Conf. Empirical Methods Natural Lang. Process.","author":"Lin"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3104310"},{"key":"ref8","first-page":"564","article-title":"DeepPath: A reinforcement learning method for knowledge graph reasoning","volume-title":"Proc. 2017 Conf. Empirical Methods Natural Lang. Process.","author":"Xiong"},{"key":"ref9","article-title":"Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning","author":"Das","year":"2017"},{"key":"ref10","first-page":"5694","article-title":"Dynamic anticipation and completion for multi-hop reasoning over sparse knowledge graph","volume-title":"Proc. 2020 Conf. Empirical Methods Natural Lang. Process.","author":"Lv"},{"key":"ref11","first-page":"1926","article-title":"Reasoning like human: Hierarchical reinforcement learning for knowledge graph reasoning","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Wan"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20538"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33398"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16565"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.107"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.412"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.232"},{"key":"ref18","first-page":"1578","article-title":"DREAM: Adaptive reinforcement learning based on attention mechanism for temporal knowledge graph reasoning","volume-title":"Proc. 46th Int. ACM SIGIR Conf. Res. Develop. Inf. Retrieval","author":"Zheng"},{"key":"ref19","first-page":"2412","article-title":"Learning long- and short-term representations for temporal knowledge graph reasoning","volume-title":"Proc. ACM Web Conf.","author":"Zhang"},{"key":"ref20","first-page":"6736","article-title":"Temporal extrapolation and knowledge transfer for lifelong temporal knowledge graph reasoning","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Chen"},{"key":"ref21","first-page":"9448","article-title":"Inductive relation prediction by subgraph reasoning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Teru"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16554"},{"key":"ref23","first-page":"4261","article-title":"Inductive relation prediction with logical reasoning using contrastive representations","volume-title":"Proc. 2022 Conf. Empirical Methods Natural Lang. Process.","author":"Pan"},{"key":"ref24","first-page":"2341","article-title":"Subgraph neighboring relations infomax for inductive link prediction on knowledge graphs","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Xu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531996"},{"key":"ref26","article-title":"Message intercommunication for inductive relation reasoning","author":"Liang","year":"2023"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.findings-emnlp.676","article-title":"Towards enhancing relational rules for knowledge graph link prediction","author":"Wu","year":"2023"},{"key":"ref28","first-page":"2787","article-title":"Translating embeddings for modeling multi-relational data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bordes"},{"key":"ref29","first-page":"809","article-title":"A three-way model for collective learning on multi-relational data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nickel"},{"key":"ref30","article-title":"Embedding entities and relations for learning and inference in knowledge bases","author":"Yang","year":"2015"},{"key":"ref31","first-page":"2071","article-title":"Complex embeddings for simple link prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Trouillon"},{"key":"ref32","first-page":"2731","article-title":"Quaternion knowledge graph embeddings","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11573"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-2053"},{"key":"ref35","article-title":"ExpressivE: A spatio-functional embedding for knowledge graph completion","author":"Pavlovic","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583358"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645451"},{"key":"ref38","first-page":"5773","article-title":"Subgraph retrieval enhanced model for multi-hop knowledge base question answering","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"Zhang"},{"key":"ref39","article-title":"Is independent learning all you need in the StarCraft multi-agent challenge?","author":"Witt","year":"2020"},{"issue":"1","key":"ref40","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref41","first-page":"29476","article-title":"Neural Bellman-Ford networks: A general graph neural network framework for link prediction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref42","first-page":"11313","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref43","first-page":"13260","article-title":"Principal neighbourhood aggregation for graph nets","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Corso"},{"key":"ref44","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512008"},{"key":"ref46","article-title":"A*Net: A scalable path-based reasoning approach for knowledge graphs","author":"Zhu","year":"2022"},{"key":"ref47","first-page":"5184","article-title":"Tucker: Tensor factorization for knowledge graph completion","volume-title":"Proc. 2019 Conf. Empirical Methods Natural Lang. Process.","author":"Balazevic"},{"key":"ref48","article-title":"RotatE: Knowledge graph embedding by relational rotation in complex space","author":"Sun","year":"2018"},{"key":"ref49","first-page":"6894","article-title":"Quaternion knowledge graph embeddings","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref50","first-page":"29476","article-title":"Neural Bellman-Ford networks: A general graph neural network framework for link prediction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref51","article-title":"RNNLogic: Learning logic rules for reasoning on knowledge graphs","author":"Qu","year":"2020"},{"key":"ref52","article-title":"DRUM: End-to-end differentiable rule mining on knowledge graphs","author":"Sadeghian","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.81"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.580"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5672-8_41"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-06162-x"},{"key":"ref57","first-page":"6787","article-title":"M-Walk: Learning to walk over graphs using Monte Carlo tree search","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shen"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3502223.3502224"},{"key":"ref59","first-page":"57","article-title":"Observed versus latent features for knowledge base and text inference","volume-title":"Proc. Workshop Continuous Vector Space Models Compositionality","author":"Toutanova"},{"key":"ref60","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11573","article-title":"Convolutional 2D knowledge graph embeddings","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Dettmers"},{"key":"ref61","first-page":"433","article-title":"Statistical predicate invention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kok"},{"key":"ref62","first-page":"2316","article-title":"Differentiable learning of logical rules for knowledge base reasoning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11329113\/11239494.pdf?arnumber=11239494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:37:15Z","timestamp":1767724635000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11239494\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":62,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2025.3631495","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}