{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T19:04:11Z","timestamp":1772910251555,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2002540"],"award-info":[{"award-number":["IIS-2002540"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Agriculture and Food Research Initiative","award":["2020-67021-32799\/project accession no.1024178"],"award-info":[{"award-number":["2020-67021-32799\/project accession no.1024178"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589335.3641241","type":"proceedings-article","created":{"date-parts":[[2024,5,12]],"date-time":"2024-05-12T18:41:21Z","timestamp":1715539281000},"page":"1246-1249","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Neural Contextual Bandits for Personalized Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3035-4849","authenticated-orcid":false,"given":"Yikun","family":"Ban","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5828-7436","authenticated-orcid":false,"given":"Yunzhe","family":"Qi","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6429-6272","authenticated-orcid":false,"given":"Jingrui","family":"He","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, IL, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","first-page":"2312","volume-title":"Advances in Neural Information Processing Systems","author":"Abbasi-Yadkori Y.","year":"2011","unstructured":"Y. Abbasi-Yadkori, D. P\u00e1l, and C. Szepesv\u00e1ri. Improved algorithms for linear stochastic bandits. In Advances in Neural Information Processing Systems, pages 2312--2320, 2011."},{"key":"e_1_3_2_2_2_1","first-page":"127","volume-title":"International Conference on Machine Learning","author":"Agrawal S.","year":"2013","unstructured":"S. Agrawal and N. Goyal. Thompson sampling for contextual bandits with linear payoffs. In International Conference on Machine Learning, pages 127--135. PMLR, 2013."},{"key":"e_1_3_2_2_3_1","volume-title":"Finite-time analysis of the multiarmed bandit problem. Machine learning, 47(2--3):235--256","author":"Auer P.","year":"2002","unstructured":"P. Auer, N. Cesa-Bianchi, and P. Fischer. Finite-time analysis of the multiarmed bandit problem. Machine learning, 47(2--3):235--256, 2002."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403134"},{"key":"e_1_3_2_2_5_1","volume-title":"Convolutional neural bandit: Provable algorithm for visualaware advertising. arXiv preprint arXiv:2107.07438","author":"Ban Y.","year":"2021","unstructured":"Y. Ban and J. He. Convolutional neural bandit: Provable algorithm for visualaware advertising. arXiv preprint arXiv:2107.07438, 2021."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450058"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467299"},{"key":"e_1_3_2_2_8_1","volume-title":"Neural collaborative filtering bandits via meta learning. arXiv preprint arXiv:2201.13395","author":"Ban Y.","year":"2022","unstructured":"Y. Ban, Y. Qi, T. Wei, and J. He. Neural collaborative filtering bandits via meta learning. arXiv preprint arXiv:2201.13395, 2022."},{"key":"e_1_3_2_2_9_1","volume-title":"International Conference on Learning Representations","author":"Ban Y.","year":"2022","unstructured":"Y. Ban, Y. Yan, A. Banerjee, and J. He. EE-net: Exploitation-exploration neural networks in contextual bandits. In International Conference on Learning Representations, 2022. URL https:\/\/openreview.net\/forum?id=X_ch3VrNSRg."},{"key":"e_1_3_2_2_10_1","first-page":"27497","article-title":"Improved algorithms for neural active learning","volume":"35","author":"Ban Y.","year":"2022","unstructured":"Y. Ban, Y. Zhang, H. Tong, A. Banerjee, and J. He. Improved algorithms for neural active learning. Advances in Neural Information Processing Systems, 35: 27497--27509, 2022.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_11_1","volume-title":"Neural exploitation and exploration of contextual bandits. arXiv preprint arXiv:2305.03784","author":"Ban Y.","year":"2023","unstructured":"Y. Ban, Y. Yan, A. Banerjee, and J. He. Neural exploitation and exploration of contextual bandits. arXiv preprint arXiv:2305.03784, 2023."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546758"},{"key":"e_1_3_2_2_13_1","volume-title":"Federated neural bandit. arXiv preprint arXiv:2205.14309","author":"Dai Z.","year":"2022","unstructured":"Z. Dai, Y. Shu, A. Verma, F. X. Fan, B. K. H. Low, and P. Jaillet. Federated neural bandit. arXiv preprint arXiv:2205.14309, 2022."},{"key":"e_1_3_2_2_14_1","volume-title":"Contextual bandits with online neural regression. arXiv preprint arXiv:2312.07145","author":"Deb R.","year":"2023","unstructured":"R. Deb, Y. Ban, S. Zuo, J. He, and A. Banerjee. Contextual bandits with online neural regression. arXiv preprint arXiv:2312.07145, 2023."},{"key":"e_1_3_2_2_15_1","first-page":"4848","volume-title":"Advances in neural information processing systems","author":"Deshmukh A. A.","year":"2017","unstructured":"A. A. Deshmukh, U. Dogan, and C. Scott. Multi-task learning for contextual bandits. In Advances in neural information processing systems, pages 4848--4856, 2017."},{"key":"e_1_3_2_2_16_1","first-page":"3199","volume-title":"International Conference on Machine Learning","author":"Foster D.","year":"2020","unstructured":"D. Foster and A. Rakhlin. Beyond ucb: Optimal and efficient contextual bandits with regression oracles. In International Conference on Machine Learning, pages 3199--3210. PMLR, 2020."},{"key":"e_1_3_2_2_17_1","volume-title":"Alleviating matthew effect of offline reinforcement learning in interactive recommendation. arXiv preprint arXiv:2307.04571","author":"Gao C.","year":"2023","unstructured":"C. Gao, K. Huang, J. Chen, Y. Zhang, B. Li, P. Jiang, S. Wang, Z. Zhang, and X. He. Alleviating matthew effect of offline reinforcement learning in interactive recommendation. arXiv preprint arXiv:2307.04571, 2023."},{"key":"e_1_3_2_2_18_1","first-page":"757","volume-title":"International Conference on Machine Learning","author":"Gentile C.","year":"2014","unstructured":"C. Gentile, S. Li, and G. Zappella. Online clustering of bandits. In International Conference on Machine Learning, pages 757--765, 2014."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305511"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_2_21_1","volume-title":"International Conference on Learning Representations","author":"Jia Y.","year":"2022","unstructured":"Y. Jia, W. Zhang, D. Zhou, Q. Gu, and H. Wang. Learning neural contextual bandits through perturbed rewards. In International Conference on Learning Representations, 2022."},{"key":"e_1_3_2_2_22_1","first-page":"240","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Kassraie P.","year":"2022","unstructured":"P. Kassraie and A. Krause. Neural contextual bandits without regret. In International Conference on Artificial Intelligence and Statistics, pages 240--278. PMLR, 2022."},{"key":"e_1_3_2_2_23_1","first-page":"1301","volume-title":"Journal of machine learning research workshop and conference proceedings","author":"Korda N.","year":"2016","unstructured":"N. Korda, B. Sz\u00f6r\u00e9nyi, and L. Shuai. Distributed clustering of linear bandits in peer to peer networks. In Journal of machine learning research workshop and conference proceedings, volume 48, pages 1301--1309. International Machine Learning Societ, 2016."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911548"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/3367243.3367445"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1835804.1835811"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599386"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539312"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599371"},{"key":"e_1_3_2_2_31_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Qi Y.","year":"2023","unstructured":"Y. Qi, Y. Ban, T. Wei, J. Zou, H. Yao, and J. He. Meta-learning with neural bandit scheduler. In Thirty-seventh Conference on Neural Information Processing Systems, 2023."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781680836219"},{"key":"e_1_3_2_2_33_1","volume-title":"A survey of collaborative filtering techniques. Advances in artificial intelligence","author":"Su X.","year":"2009","unstructured":"X. Su and T. M. Khoshgoftaar. A survey of collaborative filtering techniques. Advances in artificial intelligence, 2009, 2009."},{"key":"e_1_3_2_2_34_1","volume-title":"Finite-time analysis of kernelised contextual bandits. arXiv preprint arXiv:1309.6869","author":"Valko M.","year":"2013","unstructured":"M. Valko, N. Korda, R. Munos, I. Flaounas, and N. Cristianini. Finite-time analysis of kernelised contextual bandits. arXiv preprint arXiv:1309.6869, 2013."},{"key":"e_1_3_2_2_35_1","first-page":"2129","volume-title":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","author":"Zhao C.","year":"2021","unstructured":"J.Wu, C. Zhao, T. Yu, J. Li, and S. Li. Clustering of conversational bandits for user preference learning and elicitation. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pages 2129--2139, 2021."},{"key":"e_1_3_2_2_36_1","volume-title":"Resact: Reinforcing long-term engagement in sequential recommendation with residual actor. arXiv preprint arXiv:2206.02620","author":"Xue W.","year":"2022","unstructured":"W. Xue, Q. Cai, R. Zhan, D. Zheng, P. Jiang, and B. An. Resact: Reinforcing long-term engagement in sequential recommendation with residual actor. arXiv preprint arXiv:2206.02620, 2022."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412250"},{"key":"e_1_3_2_2_38_1","volume-title":"International Conference on Learning Representations","author":"Zhang W.","year":"2021","unstructured":"W. Zhang, D. Zhou, L. Li, and Q. Gu. Neural thompson sampling. In International Conference on Learning Representations, 2021."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3526003"}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3641241","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589335.3641241","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:39:50Z","timestamp":1755823190000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3641241"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":39,"alternative-id":["10.1145\/3589335.3641241","10.1145\/3589335"],"URL":"https:\/\/doi.org\/10.1145\/3589335.3641241","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}