{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T11:04:22Z","timestamp":1780916662784,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819214648","type":"print"},{"value":"9789819214655","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-92-1465-5_45","type":"book-chapter","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T10:15:18Z","timestamp":1780913718000},"page":"573-585","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Path Value-Aware Reinforcement Learning Method for\u00a0Knowledge Graph Question Answering"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3485-069X","authenticated-orcid":false,"given":"Zifang","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8881-0037","authenticated-orcid":false,"given":"Tong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9536-7339","authenticated-orcid":false,"given":"Yiting","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1342-3020","authenticated-orcid":false,"given":"Yani","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6058-0217","authenticated-orcid":false,"given":"Zhen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"45_CR1","doi-asserted-by":"crossref","unstructured":"Bai, L., Chai, D., Zhu, L.: RLAT: multi-hop temporal knowledge graph reasoning based on reinforcement learning and attention mechanism. Knowl.-Based Syst. 110514 (2023)","DOI":"10.1016\/j.knosys.2023.110514"},{"issue":"2","key":"45_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103242","volume":"60","author":"X Bi","year":"2023","unstructured":"Bi, X., et al.: Boosting question answering over knowledge graph with reward integration and policy evaluation under weak supervision. Inf. Process. Manage. 60(2), 103242 (2023)","journal-title":"Inf. Process. Manage."},{"key":"45_CR3","doi-asserted-by":"crossref","unstructured":"Bl\u00fcbaum, L., Heindorf, S.: Causal question answering with reinforcement learning. In: Proceedings of the ACM Web Conference 2024, pp. 2204\u20132215 (2024)","DOI":"10.1145\/3589334.3645610"},{"key":"45_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110760","volume":"276","author":"H Cui","year":"2023","unstructured":"Cui, H., Peng, T., Han, R., Han, J., Liu, L.: Path-based multi-hop reasoning over knowledge graph for answering questions via adversarial reinforcement learning. Knowl.-Based Syst. 276, 110760 (2023)","journal-title":"Knowl.-Based Syst."},{"issue":"3","key":"45_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103283","volume":"60","author":"H Cui","year":"2023","unstructured":"Cui, H., Peng, T., Han, R., Zhu, B., Bi, H., Liu, L.: Reinforcement learning with dynamic completion for answering multi-hop questions over incomplete knowledge graph. Inf. Process. Manage. 60(3), 103283 (2023)","journal-title":"Inf. Process. Manage."},{"key":"45_CR6","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1016\/j.ins.2022.11.042","volume":"619","author":"H Cui","year":"2023","unstructured":"Cui, H., Peng, T., Xiao, F., Han, J., Han, R., Liu, L.: Incorporating anticipation embedding into reinforcement learning framework for multi-hop knowledge graph question answering. Inf. Sci. 619, 745\u2013761 (2023)","journal-title":"Inf. Sci."},{"key":"45_CR7","unstructured":"Das, R., et al.: Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning. In: International Conference on Learning Representations"},{"key":"45_CR8","doi-asserted-by":"crossref","unstructured":"Dettmers, T., Minervini, P., Stenetorp, P., Riedel, S.: Convolutional 2D knowledge graph embeddings. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11573"},{"key":"45_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106833","volume":"181","author":"J Feng","year":"2025","unstructured":"Feng, J., Wang, Q., Qiu, H., Liu, L.: Retrieval in decoder benefits generative models for explainable complex question answering. Neural Netw. 181, 106833 (2025)","journal-title":"Neural Netw."},{"key":"45_CR10","doi-asserted-by":"crossref","unstructured":"Han, J., Cheng, B., Wang, X.: Two-phase hypergraph based reasoning with dynamic relations for multi-hop KBQA. In: IJCAI, pp. 3615\u20133621 (2020)","DOI":"10.24963\/ijcai.2020\/500"},{"key":"45_CR11","doi-asserted-by":"crossref","unstructured":"Heo, Y.J., Kim, E.S., Choi, W.S., Zhang, B.T.: Hypergraph transformer: Weakly-supervised multi-hop reasoning for knowledge-based visual question answering. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022), vol 1:(LONG PAPERS), pp. 373\u2013390. Assoc Computational Linguistics-ACL (2022)","DOI":"10.18653\/v1\/2022.acl-long.29"},{"key":"45_CR12","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.inffus.2022.11.022","volume":"92","author":"K Kim","year":"2023","unstructured":"Kim, K., Park, S.: AOBert: all-modalities-in-one Bert for multimodal sentiment analysis. Inf. Fusion 92, 37\u201345 (2023)","journal-title":"Inf. Fusion"},{"key":"45_CR13","doi-asserted-by":"crossref","unstructured":"Lin, X.V., Socher, R., Xiong, C.: Multi-hop knowledge graph reasoning with reward shaping. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3243\u20133253 (2018)","DOI":"10.18653\/v1\/D18-1362"},{"key":"45_CR14","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937. PMLR (2016)"},{"key":"45_CR15","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"key":"45_CR16","doi-asserted-by":"crossref","unstructured":"Qiu, Y., Wang, Y., Jin, X., Zhang, K.: Stepwise reasoning for multi-relation question answering over knowledge graph with weak supervision. In: Proceedings of the 13th International Conference on web Search and Data Mining, pp. 474\u2013482 (2020)","DOI":"10.1145\/3336191.3371812"},{"key":"45_CR17","doi-asserted-by":"crossref","unstructured":"Sun, H., Bedrax-Weiss, T., Cohen, W.W.: Pullnet: open domain question answering with iterative retrieval on knowledge bases and text. arXiv preprint arXiv:1904.09537 (2019)","DOI":"10.18653\/v1\/D19-1242"},{"key":"45_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121880","volume":"238","author":"Z Tang","year":"2024","unstructured":"Tang, Z., Li, T., Wu, D., Liu, J., Yang, Z.: A systematic literature review of reinforcement learning-based knowledge graph research. Expert Syst. Appl. 238, 121880 (2024)","journal-title":"Expert Syst. Appl."},{"key":"45_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neunet.2020.11.012","volume":"135","author":"P Tiwari","year":"2021","unstructured":"Tiwari, P., Zhu, H., Pandey, H.M.: Dapath: distance-aware knowledge graph reasoning based on deep reinforcement learning. Neural Netw. 135, 1\u201312 (2021)","journal-title":"Neural Netw."},{"issue":"8","key":"45_CR20","doi-asserted-by":"publisher","first-page":"3757","DOI":"10.1007\/s00500-022-06843-0","volume":"26","author":"T Vo","year":"2022","unstructured":"Vo, T.: An integrated network embedding with reinforcement learning for explainable recommendation. Soft. Comput. 26(8), 3757\u20133775 (2022)","journal-title":"Soft. Comput."},{"key":"45_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105910","volume":"197","author":"Q Wang","year":"2020","unstructured":"Wang, Q., Hao, Y., Cao, J.: ADRL: an attention-based deep reinforcement learning framework for knowledge graph reasoning. Knowl.-Based Syst. 197, 105910 (2020)","journal-title":"Knowl.-Based Syst."},{"key":"45_CR22","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/978-3-030-88480-2_22","volume-title":"Natural Language Processing and Chinese Computing","author":"S Wang","year":"2021","unstructured":"Wang, S., Chen, X., Xiong, S.: Attention based reinforcement learning with reward shaping for knowledge graph reasoning. In: Wang, L., Feng, Y., Hong, Yu., He, R. (eds.) NLPCC 2021, Part I. LNCS (LNAI), vol. 13028, pp. 275\u2013287. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-88480-2_22"},{"key":"45_CR23","doi-asserted-by":"crossref","unstructured":"Wang, X., Liu, K., Wang, D., Wu, L., Fu, Y., Xie, X.: Multi-level recommendation reasoning over knowledge graphs with reinforcement learning. In: Proceedings of the ACM Web Conference 2022, pp. 2098\u20132108 (2022)","DOI":"10.1145\/3485447.3512083"},{"key":"45_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-030-73197-7_32","volume-title":"Database Systems for Advanced Applications","author":"Y Wang","year":"2021","unstructured":"Wang, Y., Zhang, H.: BIRL: bidirectional-interaction reinforcement learning framework for joint relation and entity extraction. In: Jensen, C.S., et al. (eds.) DASFAA 2021, Part II. LNCS, vol. 12682, pp. 483\u2013499. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-73197-7_32"},{"key":"45_CR25","doi-asserted-by":"crossref","unstructured":"Wu, Y., Huang, Y., Hu, N., Hua, Y., Qi, G., Chen, J., Pan, J.: Cotkr: chain-of-thought enhanced knowledge rewriting for complex knowledge graph question answering. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 3501\u20133520 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.205"},{"key":"45_CR26","doi-asserted-by":"crossref","unstructured":"Xiong, W., Hoang, T., Wang, W.Y.: Deeppath: a reinforcement learning method for knowledge graph reasoning. arXiv preprint arXiv:1707.06690 (2017)","DOI":"10.18653\/v1\/D17-1060"},{"key":"45_CR27","doi-asserted-by":"crossref","unstructured":"Xu, D., et al.: Harnessing large language models for knowledge graph question answering via adaptive multi-aspect retrieval-augmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 25570\u201325578 (2025)","DOI":"10.1609\/aaai.v39i24.34747"},{"key":"45_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Qian, Y., Ye, Y., Zhang, C.: Adapting distilled knowledge for few-shot relation reasoning over knowledge graphs. In: Proceedings of the 2022 SIAM International Conference on Data Mining (SDM), pp. 666\u2013674. SIAM (2022)","DOI":"10.1137\/1.9781611977172.75"},{"key":"45_CR29","unstructured":"Zhou, M., Huang, M., Zhu, X.: An interpretable reasoning network for multi-relation question answering. In: Proceedings of the 27th International Conference on Computational Linguistics, pp. 2010\u20132022 (2018)"},{"key":"45_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108843","volume":"248","author":"A Zhu","year":"2022","unstructured":"Zhu, A., Ouyang, D., Liang, S., Shao, J.: Step by step: a hierarchical framework for multi-hop knowledge graph reasoning with reinforcement learning. Knowl.-Based Syst. 248, 108843 (2022)","journal-title":"Knowl.-Based Syst."},{"key":"45_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128994","volume":"617","author":"Y Zhu","year":"2025","unstructured":"Zhu, Y., Ma, T., Sun, S., Rong, H., Bian, Y., Huang, K.: RTA: a reinforcement learning-based temporal knowledge graph question answering model. Neurocomputing 617, 128994 (2025)","journal-title":"Neurocomputing"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-1465-5_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T10:15:32Z","timestamp":1780913732000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-1465-5_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819214648","9789819214655"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-1465-5_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pakdd2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}