{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T07:57:08Z","timestamp":1778313428196,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Shenzhen Science and Technology Program","award":["RCYX20200714114523079"],"award-info":[{"award-number":["RCYX20200714114523079"]}]},{"name":"the Key-Area Research and Development Program of Guangdong Province","award":["2020B0909050003"],"award-info":[{"award-number":["2020B0909050003"]}]},{"name":"the Fellowship of China Postdoctoral Science Foundation","award":["2021TQ0027 and 2022M710006"],"award-info":[{"award-number":["2021TQ0027 and 2022M710006"]}]},{"name":"the National Key Research and Development Program of China","award":["2022YFB3104702"],"award-info":[{"award-number":["2022YFB3104702"]}]},{"name":"the National Natural Science Foundation of China","award":["62272262"],"award-info":[{"award-number":["62272262"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543507.3583856","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T23:30:51Z","timestamp":1682551851000},"page":"4041-4049","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Breaking Filter Bubble: A Reinforcement Learning Framework of Controllable Recommender System"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4688-8354","authenticated-orcid":false,"given":"Zhenyang","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2649-2061","authenticated-orcid":false,"given":"Yancheng","family":"Dong","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7561-5646","authenticated-orcid":false,"given":"Chen","family":"Gao","sequence":"additional","affiliation":[{"name":"Tsinghua University, China and Huawei Noah's Ark Lab, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2975-0783","authenticated-orcid":false,"given":"Yizhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8800-1483","authenticated-orcid":false,"given":"Dong","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0422-8235","authenticated-orcid":false,"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5826-3765","authenticated-orcid":false,"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, China and Research Institute of Tsinghua, Pearl River Delta, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5617-1659","authenticated-orcid":false,"given":"Yong","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5462-6178","authenticated-orcid":false,"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua-Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, China and Peng Cheng Laboratory, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Reinforcement learning based recommender systems: A survey. ACM Computing Surveys (CSUR)","author":"Afsar M\u00a0Mehdi","year":"2021","unstructured":"M\u00a0Mehdi Afsar, Trafford Crump, and Behrouz Far. 2021. Reinforcement learning based recommender systems: A survey. ACM Computing Surveys (CSUR) (2021)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412246"},{"key":"e_1_3_2_1_3_1","volume-title":"Twenty-Fourth International Joint Conference on Artificial Intelligence.","author":"Ashkan Azin","year":"2015","unstructured":"Azin Ashkan, Branislav Kveton, Shlomo Berkovsky, and Zheng Wen. 2015. Optimal greedy diversity for recommendation. In Twenty-Fourth International Joint Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2008\/10\/P10008"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403344"},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Machine Learning. PMLR, 1052\u20131061","author":"Chen Xinshi","year":"2019","unstructured":"Xinshi Chen, Shuang Li, Hui Li, Shaohua Jiang, Yuan Qi, and Le Song. 2019. Generative adversarial user model for reinforcement learning based recommendation system. In International Conference on Machine Learning. PMLR, 1052\u20131061."},{"key":"e_1_3_2_1_7_1","volume-title":"User Movement in Location-Based Social Networks ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD).","author":"Cho Eunjoon","year":"2011","unstructured":"Eunjoon Cho, Seth\u00a0A Myers, and Jure Leskovec. 2011. Friendship and mobility: Friendship and mobility: User movement in location-based social networksfriendship and mobility. In User Movement in Location-Based Social Networks ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2023301118"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Wenqi Fan Yao Ma Qing Li Yuan He Eric Zhao Jiliang Tang and Dawei Yin. 2019. Graph neural networks for social recommendation. In The world wide web conference. 417\u2013426.","DOI":"10.1145\/3308558.3313488"},{"key":"e_1_3_2_1_10_1","volume-title":"A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions. ACM Transactions on Recommender Systems (TORS)","author":"Gao Chen","year":"2021","unstructured":"Chen Gao, Yu Zheng, Nian Li, Yinfeng Li, Yingrong Qin, Jinghua Piao, Yuhan Quan, Jianxin Chang, Depeng Jin, Xiangnan He, and Yong Li. 2021. A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions. ACM Transactions on Recommender Systems (TORS) (2021)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531890"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498487"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_1_15_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_16_1","volume-title":"Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations (ICLR).","author":"N.","unstructured":"Thomas\u00a0N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3535335"},{"key":"e_1_3_2_1_19_1","volume-title":"Diversity in recommender systems\u2013A survey. Knowledge-based systems 123","author":"Kunaver Matev\u017e","year":"2017","unstructured":"Matev\u017e Kunaver and Toma\u017e Po\u017erl. 2017. Diversity in recommender systems\u2013A survey. Knowledge-based systems 123 (2017), 154\u2013162."},{"key":"e_1_3_2_1_20_1","volume-title":"Deep reinforcement learning based recommendation with explicit user-item interactions modeling. arXiv preprint arXiv:1810.12027","author":"Liu Feng","year":"2018","unstructured":"Feng Liu, Ruiming Tang, Xutao Li, Weinan Zhang, Yunming Ye, Haokun Chen, Huifeng Guo, and Yuzhou Zhang. 2018. Deep reinforcement learning based recommendation with explicit user-item interactions modeling. arXiv preprint arXiv:1810.12027 (2018)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412152"},{"key":"e_1_3_2_1_22_1","volume-title":"Human-level control through deep reinforcement learning. nature 518, 7540","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei\u00a0A Rusu, Joel Veness, Marc\u00a0G Bellemare, Alex Graves, Martin Riedmiller, Andreas\u00a0K Fidjeland, Georg Ostrovski, 2015. Human-level control through deep reinforcement learning. nature 518, 7540 (2015), 529\u2013533."},{"key":"e_1_3_2_1_23_1","volume-title":"Human-level control through deep reinforcement learning. nature","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei\u00a0A Rusu, Joel Veness, Marc\u00a0G Bellemare, Alex Graves, Martin Riedmiller, Andreas\u00a0K Fidjeland, Georg Ostrovski, 2015. Human-level control through deep reinforcement learning. nature (2015)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2566486.2568012"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2015.01.007"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3478879"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308560.3317303"},{"key":"e_1_3_2_1_29_1","volume-title":"Learning to predict by the methods of temporal differences. Machine learning 3, 1","author":"Sutton S","year":"1988","unstructured":"Richard\u00a0S Sutton. 1988. Learning to predict by the methods of temporal differences. Machine learning 3, 1 (1988), 9\u201344."},{"key":"e_1_3_2_1_30_1","volume-title":"User-controllable Recommendation Against Filter Bubbles. arXiv preprint arXiv:2204.13844","author":"Wang Wenjie","year":"2022","unstructured":"Wenjie Wang, Fuli Feng, Liqiang Nie, and Tat-Seng Chua. 2022. User-controllable Recommendation Against Filter Bubbles. arXiv preprint arXiv:2204.13844 (2022)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331267"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512083"},{"key":"e_1_3_2_1_33_1","volume-title":"A survey on accuracy-oriented neural recommendation: From collaborative filtering to information-rich recommendation","author":"Wu Le","year":"2022","unstructured":"Le Wu, Xiangnan He, Xiang Wang, Kun Zhang, and Meng Wang. 2022. A survey on accuracy-oriented neural recommendation: From collaborative filtering to information-rich recommendation. IEEE Transactions on Knowledge and Data Engineering (2022)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301346"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3151618"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3158369"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412095"}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583856","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:03Z","timestamp":1750178823000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583856"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":37,"alternative-id":["10.1145\/3543507.3583856","10.1145\/3543507"],"URL":"https:\/\/doi.org\/10.1145\/3543507.3583856","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}