{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T20:42:46Z","timestamp":1742935366704,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819991181"},{"type":"electronic","value":"9789819991198"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-9119-8_42","type":"book-chapter","created":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T13:03:04Z","timestamp":1706878984000},"page":"463-475","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Reinforcement Learning Approach for\u00a0Personalized Diversity in\u00a0Feeds Recommendation"],"prefix":"10.1007","author":[{"given":"Li","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kangqi","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuoye","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Bai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,3]]},"reference":[{"key":"42_CR1","doi-asserted-by":"crossref","unstructured":"Abdool, M., et al.: Managing diversity in Airbnb search. In: SIGKDD, pp. 2952\u20132960. ACM (2020)","DOI":"10.1145\/3394486.3403345"},{"issue":"5","key":"42_CR2","doi-asserted-by":"publisher","first-page":"896","DOI":"10.1109\/TKDE.2011.15","volume":"24","author":"G Adomavicius","year":"2012","unstructured":"Adomavicius, G., Kwon, Y.: Improving aggregate recommendation diversity using ranking-based techniques. IEEE Trans. Knowl. Data Eng. 24(5), 896\u2013911 (2012)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"42_CR3","doi-asserted-by":"crossref","unstructured":"Ai, Q., Bi, K., Guo, J., Croft, W.B.: Learning a deep listwise context model for ranking refinement. In: SIGIR, pp. 135\u2013144. ACM (2018)","DOI":"10.1145\/3209978.3209985"},{"key":"42_CR4","doi-asserted-by":"crossref","unstructured":"Ai, Q., Wang, X., Bruch, S., Golbandi, N., Bendersky, M., Najork, M.: Learning groupwise multivariate scoring functions using deep neural networks. In: SIGIR, pp. 85\u201392. ACM (2019)","DOI":"10.1145\/3341981.3344218"},{"key":"42_CR5","unstructured":"Ashkan, A., Kveton, B., Berkovsky, S., Wen, Z.: Optimal greedy diversity for recommendation. In: IJCAI, pp. 1742\u20131748 (2015)"},{"key":"42_CR6","unstructured":"Bai, X., Guan, J., Wang, H.: A model-based reinforcement learning with adversarial training for online recommendation. In: NeurIPS, pp. 10734\u201310745 (2019)"},{"key":"42_CR7","unstructured":"Bello, I., et al.: Seq2Slate: re-ranking and slate optimization with RNNs. CoRR abs\/1810.02019 (2018)"},{"key":"42_CR8","unstructured":"Chen, L., Zhang, G., Zhou, E.: Fast greedy MAP inference for determinantal point process to improve recommendation diversity. In: NeurIPS, pp. 5627\u20135638 (2018)"},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Chen, M., Beutel, A., Covington, P., Jain, S., Belletti, F., Chi, E.H.: Top-K off-policy correction for a REINFORCE recommender system. In: WSDM, pp. 456\u2013464. ACM (2019)","DOI":"10.1145\/3289600.3290999"},{"key":"42_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, P., Wang, S., Ma, J., Sun, J., Xiong, H.: Learning to recommend accurate and diverse items. In: WWW, pp. 183\u2013192. ACM (2017)","DOI":"10.1145\/3038912.3052585"},{"key":"42_CR11","unstructured":"Cortes, C., Mansour, Y., Mohri, M.: Learning bounds for importance weighting. In: NeurIPS, pp. 442\u2013450. Curran Associates, Inc. (2010)"},{"key":"42_CR12","doi-asserted-by":"crossref","unstructured":"Eskandanian, F., Mobasher, B., Burke, R.: A clustering approach for personalizing diversity in collaborative recommender systems. In: UMAP, pp. 280\u2013284. ACM (2017)","DOI":"10.1145\/3079628.3079699"},{"key":"42_CR13","unstructured":"Gelada, C., Kumar, S., Buckman, J., Nachum, O., Bellemare, M.G.: DeepMDP: learning continuous latent space models for representation learning. In: ICML, vol. 97, pp. 2170\u20132179. PMLR (2019)"},{"key":"42_CR14","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.knosys.2017.03.023","volume":"125","author":"A Gogna","year":"2017","unstructured":"Gogna, A., Majumdar, A.: Balancing accuracy and diversity in recommendations using matrix completion framework. Knowl. Based Syst. 125, 83\u201395 (2017)","journal-title":"Knowl. Based Syst."},{"key":"42_CR15","doi-asserted-by":"crossref","unstructured":"Gong, Y., et al.: Exact-K recommendation via maximal clique optimization. In: SIGKDD, pp. 617\u2013626. ACM (2019)","DOI":"10.1145\/3292500.3330832"},{"key":"42_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"42_CR17","doi-asserted-by":"crossref","unstructured":"Lalmas, M., O\u2019Brien, H., Yom-Tov, E.: Measuring User Engagement. Synthesis Lectures on Information Concepts, Retrieval, and Services. Morgan & Claypool Publishers (2014)","DOI":"10.1007\/978-3-031-02289-0"},{"key":"42_CR18","doi-asserted-by":"crossref","unstructured":"Li, J., Ren, P., Chen, Z., Ren, Z., Lian, T., Ma, J.: Neural attentive session-based recommendation. In: CIKM, pp. 1419\u20131428. ACM (2017)","DOI":"10.1145\/3132847.3132926"},{"key":"42_CR19","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. CoRR abs\/1312.5602 (2013)"},{"key":"42_CR20","unstructured":"Munos, R., Stepleton, T., Harutyunyan, A., Bellemare, M.G.: Safe and efficient off-policy reinforcement learning. arXiv preprint arXiv:1606.02647 (2016)"},{"key":"42_CR21","unstructured":"Noia, T.D., Ostuni, V.C., Rosati, J., Tomeo, P., Sciascio, E.D.: An analysis of users\u2019 propensity toward diversity in recommendations. In: RecSys, pp. 285\u2013288. ACM (2014)"},{"key":"42_CR22","doi-asserted-by":"crossref","unstructured":"Pradel, B., et al.: A case study in a recommender system based on purchase data. In: SIGKDD, pp. 377\u2013385. ACM (2011)","DOI":"10.1145\/2020408.2020470"},{"key":"42_CR23","unstructured":"Precup, D., Sutton, R.S., Dasgupta, S.: Off-policy temporal-difference learning with function approximation. In: ICML, pp. 417\u2013424 (2001)"},{"key":"42_CR24","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning - An Introduction. Adaptive Computation and Machine Learning. MIT Press, Cambridge (1998)"},{"key":"42_CR25","first-page":"1731","volume":"16","author":"A Swaminathan","year":"2015","unstructured":"Swaminathan, A., Joachims, T.: Batch learning from logged bandit feedback through counterfactual risk minimization. J. Mach. Learn. Res. 16, 1731\u20131755 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"42_CR26","unstructured":"Wang, F., et al.: Sequential evaluation and generation framework for combinatorial recommender system. CoRR abs\/1902.00245 (2019)"},{"key":"42_CR27","unstructured":"Wang, Y., et al.: Personalized re-ranking for improving diversity in live recommender systems. CoRR abs\/2004.06390 (2020)"},{"key":"42_CR28","unstructured":"Wei, J., Zeng, A., Wu, Y., Guo, P., Hua, Q., Cai, Q.: Generator and critic: a deep reinforcement learning approach for slate re-ranking in e-commerce. CoRR abs\/2005.12206 (2020)"},{"key":"42_CR29","doi-asserted-by":"crossref","unstructured":"Wilhelm, M., Ramanathan, A., Bonomo, A., Jain, S., Chi, E.H., Gillenwater, J.: Practical diversified recommendations on Youtube with determinantal point processes. In: CIKM, pp. 2165\u20132173. ACM (2018)","DOI":"10.1145\/3269206.3272018"},{"key":"42_CR30","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"42_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, X., Xia, L., Tang, J., Yin, D.: Deep reinforcement learning for search, recommendation, and online advertising: a survey. SIGWEB Newsl. 2019(Spring), 4:1\u20134:15 (2019)","DOI":"10.1145\/3320496.3320500"},{"key":"42_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, X., Xia, L., Zhang, L., Ding, Z., Yin, D., Tang, J.: Deep reinforcement learning for page-wise recommendations. In: RecSys, pp. 95\u2013103. ACM (2018)","DOI":"10.1145\/3240323.3240374"},{"key":"42_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, X., Zhang, L., Ding, Z., Yin, D., Zhao, Y., Tang, J.: Deep reinforcement learning for list-wise recommendations. CoRR abs\/1801.00209 (2018)","DOI":"10.1145\/3240323.3240374"},{"key":"42_CR34","doi-asserted-by":"crossref","unstructured":"Zheng, G., et al.: DRN: a deep reinforcement learning framework for news recommendation. In: WWW, pp. 167\u2013176. ACM (2018)","DOI":"10.1145\/3178876.3185994"},{"key":"42_CR35","doi-asserted-by":"crossref","unstructured":"Zhuang, T., Ou, W., Wang, Z.: Globally optimized mutual influence aware ranking in e-commerce search. In: IJCAI, pp. 3725\u20133731 (2018)","DOI":"10.24963\/ijcai.2018\/518"},{"key":"42_CR36","doi-asserted-by":"crossref","unstructured":"Zou, L., Xia, L., Ding, Z., Song, J., Liu, W., Yin, D.: Reinforcement learning to optimize long-term user engagement in recommender systems. In: SIGKDD, pp. 2810\u20132818. ACM (2019)","DOI":"10.1145\/3292500.3330668"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-9119-8_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T13:11:47Z","timestamp":1706879507000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-9119-8_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819991181","9789819991198"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-9119-8_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CAAI International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Fuzhou","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cicai.caai.cn\/#\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"376","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"101","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"16","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.9","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.9","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}