{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:06:17Z","timestamp":1755907577791,"version":"3.44.0"},"reference-count":50,"publisher":"Association for Computing Machinery (ACM)","issue":"7","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2025,8,31]]},"abstract":"<jats:p>\n            Knowledge Graphs (KGs) are extensively used in recommendation systems and information retrieval but often suffer from incompleteness. A popular solution to this problem is multi-hop inference through a reinforcement learning framework, which provides an interpretable path for predicting missing links in KGs. Most previous work focuses on improving the performance of multi-hop link prediction. However, it has been observed that many multi-hop paths generated by these methods are irrational; they often fail to reasonably explain the predicted answer entities. To address this challenge, we introduce the\n            <jats:bold>Joint Multi-hop Link Prediction (JMLP)<\/jats:bold>\n            framework. The framework consists of a relation attention network and an entity attention network, which collaboratively generate the reasoning paths. The relation attention module utilizes an induction network to encode historical paths and employs the graph self-attention mechanism to refine the interaction of relation contextual information. The entity attention module uses the graph attention mechanism to obtain the aggregated contextual features and leverages self-attention to strengthen the correlation between local and global contextual entity features. Extensive experiments on five datasets validate the effectiveness of our approach, demonstrating significant improvements both in predictive performance and interpretability compared to state-of-the-art methods.\n          <\/jats:p>","DOI":"10.1145\/3737702","type":"journal-article","created":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T10:01:02Z","timestamp":1751882462000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Graph Self-attention Mechanism for Interpretable Multi-hop Knowledge Graph Link Prediction"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3459-3580","authenticated-orcid":false,"given":"Hao","family":"Liu","sequence":"first","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7313-4374","authenticated-orcid":false,"given":"Dong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6381-8702","authenticated-orcid":false,"given":"Bing","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2552-819X","authenticated-orcid":false,"given":"Wei","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2435-4957","authenticated-orcid":false,"given":"Dongjie","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2025,8,21]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1522"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3418512"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"e_1_3_1_5_2","article-title":"Translating embeddings for modeling multi-relational data","volume":"26","author":"Bordes Antoine","year":"2013","unstructured":"Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. In Proceedings of Advances in Neural Information Processing Systems, Vol. 26.","journal-title":"Proceedings of Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1133"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.376"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.112948"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103283"},{"key":"e_1_3_1_10_2","article-title":"Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning","author":"Das Rajarshi","year":"2018","unstructured":"Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishnamurthy, Alex Smola, and Andrew McCallum. 2018. Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning. In Proceedings of the International Conference on Learning Representations.","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11573"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.99"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3019893"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271704"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_1_16_2","first-page":"4687","article-title":"Rule-aware reinforcement learning for knowledge graph reasoning","author":"Hou Zhongni","year":"2021","unstructured":"Zhongni Hou, Xiaolong Jin, Zixuan Li, and Long Bai. 2021. Rule-aware reinforcement learning for knowledge graph reasoning. In Findings of the Association for Computational Linguistics, 4687\u20134692.","journal-title":"Findings of the Association for Computational Linguistics"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.232"},{"key":"e_1_3_1_18_2","article-title":"Adam: A method for stochastic optimization","author":"Kingma D. P.","year":"2014","unstructured":"D. P. Kingma. 2014. Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations.","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273551"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.688"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102093"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1362"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9491"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108235"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539289"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.700"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1334"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.06.008"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1466"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3424672"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2970044"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1174"},{"key":"e_1_3_1_34_2","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107 Petar","year":"2018","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of the International Conference on Learning Representations.","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/2629489"},{"key":"e_1_3_1_36_2","article-title":"Reasoning like human: Hierarchical reinforcement learning for knowledge graph reasoning","author":"Wan Guojia","year":"2021","unstructured":"Guojia Wan, Shirui Pan, Chen Gong, Chuan Zhou, and Gholamreza Haffari. 2021. Reasoning like human: Hierarchical reinforcement learning for knowledge graph reasoning. In Proceedings of the International Joint Conference on Artificial Intelligence.","journal-title":"Proceedings of the International Joint Conference on Artificial Intelligence"},{"key":"e_1_3_1_37_2","first-page":"1638","volume-title":"IEEE Trans. Knowl. Data Eng","volume":"36","author":"Wang Dan","year":"2023","unstructured":"Dan Wang, Bo Li, Bin Song, Chen Chen, and F. Richard Yu. 2023. HSMH: A hierarchical sequence multi-hop reasoning model with reinforcement learning. IEEE Trans. Knowl. Data Eng. 36, 4 (2023), 1638\u20131649."},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3533017"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3161804"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2754499"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3427585"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3639472"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127673"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1060"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.523"},{"issue":"2","key":"e_1_3_1_47_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3470783","article-title":"KRAN: Knowledge refining attention network for recommendation","volume":"16","author":"Zhang Zhenyu","year":"2021","unstructured":"Zhenyu Zhang, Lei Zhang, Dingqi Yang, and Liu Yang. 2021. KRAN: Knowledge refining attention network for recommendation. ACM Trans. Knowl. Discov. Data 16, 2 (2021), 1\u201320.","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3502223.3502224"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553534"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108843"},{"key":"e_1_3_1_51_2","article-title":"A* net: A scalable path-based reasoning approach for knowledge graphs","volume":"36","author":"Zhu Zhaocheng","year":"2024","unstructured":"Zhaocheng Zhu, Xinyu Yuan, Michael Galkin, Louis-Pascal Xhonneux, Ming Zhang, Maxime Gazeau, and Jian Tang. 2024. A* net: A scalable path-based reasoning approach for knowledge graphs. In Proceedings of Advances in Neural Information Processing Systems, Vol. 36 (2024).","journal-title":"Proceedings of Advances in Neural Information Processing Systems"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3737702","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T08:08:23Z","timestamp":1755850103000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3737702"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,21]]},"references-count":50,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,8,31]]}},"alternative-id":["10.1145\/3737702"],"URL":"https:\/\/doi.org\/10.1145\/3737702","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"type":"print","value":"1556-4681"},{"type":"electronic","value":"1556-472X"}],"subject":[],"published":{"date-parts":[[2025,8,21]]},"assertion":[{"value":"2024-08-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}