{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:08:22Z","timestamp":1775815702934,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,2,11]],"date-time":"2022-02-11T00:00:00Z","timestamp":1644537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,2,11]]},"DOI":"10.1145\/3488560.3498487","type":"proceedings-article","created":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T21:42:57Z","timestamp":1644961377000},"page":"316-324","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":68,"title":["Toward Pareto Efficient Fairness-Utility Trade-off in Recommendation through Reinforcement Learning"],"prefix":"10.1145","author":[{"given":"Yingqiang","family":"Ge","sequence":"first","affiliation":[{"name":"Rutgers University, Piscataway, NJ, USA"}]},{"given":"Xiaoting","family":"Zhao","sequence":"additional","affiliation":[{"name":"Etsy Inc., New York City, NY, USA"}]},{"given":"Lucia","family":"Yu","sequence":"additional","affiliation":[{"name":"Etsy Inc., New York City, NY, USA"}]},{"given":"Saurabh","family":"Paul","sequence":"additional","affiliation":[{"name":"Etsy Inc., New York City, NY, USA"}]},{"given":"Diane","family":"Hu","sequence":"additional","affiliation":[{"name":"Etsy Inc., New York City, NY, USA"}]},{"given":"Chu-Cheng","family":"Hsieh","sequence":"additional","affiliation":[{"name":"Etsy Inc., New York City, NY, USA"}]},{"given":"Yongfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Rutgers University, New Brunswick, NJ, USA"}]}],"member":"320","published-online":{"date-parts":[[2022,2,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3109859.3109912"},{"key":"e_1_3_2_1_2_1","volume-title":"The unfairness of popularity bias in recommendation. arXiv preprint arXiv:1907.13286","author":"Abdollahpouri Himan","year":"2019","unstructured":"Himan Abdollahpouri, Masoud Mansoury, Robin Burke, and Bamshad Mobasher. 2019. The unfairness of popularity bias in recommendation. arXiv preprint arXiv:1907.13286 (2019)."},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Machine Learning. PMLR, 11--20","author":"Abels Axel","year":"2019","unstructured":"Axel Abels, Diederik Roijers, Tom Lenaerts, Ann Now\u00e9 , and Denis Steckelmacher. 2019. Dynamic weights in multi-objective deep reinforcement learning. In International Conference on Machine Learning. PMLR, 11--20."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330745"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287601"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013312"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 15th WSDM .","author":"Chen Hanxiong","year":"2022","unstructured":"Hanxiong Chen, Li Yunqi, Shi Shaoyun, Shuchang Liu, He Zhu, and Yongfeng Zhang. 2022. Graph Logic Reasoning for Recommendation and Link Prediction. In Proceedings of the 15th WSDM ."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems .","author":"Chen Le","unstructured":"Le Chen, Ruijun Ma, Anik\u00f3 Hann\u00e1 k, and Christo Wilson. [n.d.]. Investigating the Impact of Gender on Rank in Resume Search Engines. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems ."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_1_10_1","unstructured":"Kyunghyun Cho Bart van Merrienboer Dzmitry Bahdanau and Yoshua Bengio. 2014. On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. In SSST@EMNLP ."},{"key":"e_1_3_2_1_11_1","unstructured":"Gabriel Dulac-Arnold Richard Evans Peter Sunehag and Ben Coppin. 2015. Reinforcement Learning in Large Discrete Action Spaces. (2015). arxiv: 1512.07679"},{"key":"e_1_3_2_1_12_1","volume-title":"ICML 2020 .","author":"Dutta Sanghamitra","year":"2020","unstructured":"Sanghamitra Dutta, Dennis Wei, Hazar Yueksel, Pin-Yu Chen, Sijia Liu, and Kush Varshney. 2020. Is there a trade-off between fairness and accuracy? a perspective using mismatched hypothesis testing. In ICML 2020 ."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401051"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462807"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441824"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401056"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401431"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330691"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2507157.2507226"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1864708.1864723"},{"key":"e_1_3_2_1_21_1","volume-title":"Pareto Efficient Fairness in Supervised Learning: From Extraction to Tracing. arXiv preprint arXiv:2104.01634","author":"Kamani Mohammad Mahdi","year":"2021","unstructured":"Mohammad Mahdi Kamani, Rana Forsati, James Z Wang, and Mehrdad Mahdavi. 2021. Pareto Efficient Fairness in Supervised Learning: From Extraction to Tracing. arXiv preprint arXiv:2104.01634 (2021)."},{"key":"e_1_3_2_1_22_1","volume-title":"The ethical algorithm: The science of socially aware algorithm design","author":"Kearns Michael","unstructured":"Michael Kearns and Aaron Roth. 2019. The ethical algorithm: The science of socially aware algorithm design .Oxford University Press."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449866"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462966"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462814"},{"key":"e_1_3_2_1_27_1","volume-title":"Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra.","author":"Lillicrap Timothy P.","year":"2016","unstructured":"Timothy P. Lillicrap, Jonathan J. Hunt, Alexander Pritzel, Nicolas Manfred Otto Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. 2016. Continuous control with deep reinforcement learning. CoRR , Vol. abs\/1509.02971 (2016)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346998"},{"key":"e_1_3_2_1_29_1","volume-title":"Advances in Neural Information Processing Systems. Curran Associates","author":"Lipton Zachary","unstructured":"Zachary Lipton, Julian McAuley, and Alexandra Chouldechova. 2018. Does mitigating MLtextquotesingle s impact disparity require treatment disparity?. In Advances in Neural Information Processing Systems. Curran Associates, Inc."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330707"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1282100.1282114"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1557914.1557930"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1125451.1125659"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313404"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the 25th conference on uncertainty in artificial intelligence. AUAI Press, 452--461","author":"Rendle Steffen","year":"2009","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In Proceedings of the 25th conference on uncertainty in artificial intelligence. AUAI Press, 452--461."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2365952.2365962"},{"key":"e_1_3_2_1_37_1","first-page":"1","article-title":"Multiobjective pareto-efficient approaches for recommender systems","volume":"5","author":"Ribeiro Marco Tulio","year":"2014","unstructured":"Marco Tulio Ribeiro, Nivio Ziviani, Edleno Silva De Moura, Itamar Hata, Anisio Lacerda, and Adriano Veloso. 2014. Multiobjective pareto-efficient approaches for recommender systems. ACM TIST , Vol. 5, 4 (2014), 1--20.","journal-title":"ACM TIST"},{"key":"e_1_3_2_1_38_1","article-title":"An MDP-based recommender system","volume":"6","author":"Shani Guy","year":"2005","unstructured":"Guy Shani, David Heckerman, and Ronen I Brafman. 2005. An MDP-based recommender system. Journal of Machine Learning Research , Vol. 6, Sep (2005).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_39_1","volume-title":"Thomas Degris, Daan Wierstra, and Martin A. Riedmiller.","author":"Silver David","year":"2014","unstructured":"David Silver, Guy Lever, Nicolas Manfred Otto Heess, Thomas Degris, Daan Wierstra, and Martin A. Riedmiller. 2014. Deterministic Policy Gradient Algorithms. In ICML ."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220088"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482420"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339574"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331267"},{"key":"e_1_3_2_1_44_1","volume-title":"Multi-FR: A Multi-Objective Optimization Method for Achieving Two-sided Fairness in E-commerce Recommendation. arXiv preprint arXiv:2105.02951","author":"Wu Haolun","year":"2021","unstructured":"Haolun Wu, Chen Ma, Bhaskar Mitra, Fernando Diaz, and Xue Liu. 2021. Multi-FR: A Multi-Objective Optimization Method for Achieving Two-sided Fairness in E-commerce Recommendation. arXiv preprint arXiv:2105.02951 (2021)."},{"key":"e_1_3_2_1_45_1","volume-title":"Gerard De Melo, and Yongfeng Zhang","author":"Xian Yikun","year":"2019","unstructured":"Yikun Xian, Zuohui Fu, S Muthukrishnan, Gerard De Melo, and Yongfeng Zhang. 2019. Reinforcement knowledge graph reasoning for explainable recommendation. In SIGIR ."},{"key":"e_1_3_2_1_46_1","volume-title":"Shan Muthukrishnan, and Yongfeng Zhang.","author":"Xian Yikun","year":"2020","unstructured":"Yikun Xian, Zuohui Fu, Handong Zhao, Yingqiang Ge, Xu Chen, Qiaoying Huang, Shijie Geng, Zhou Qin, Gerard De Melo, Shan Muthukrishnan, and Yongfeng Zhang. 2020. CAFE: Coarse-to-fine neural symbolic reasoning for explainable recommendation. In CIKM ."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450039"},{"key":"e_1_3_2_1_48_1","volume-title":"Causal Collaborative Filtering. arXiv preprint arXiv:2102.01868","author":"Xu Shuyuan","year":"2021","unstructured":"Shuyuan Xu, Yingqiang Ge, Yunqi Li, Zuohui Fu, Xu Chen, and Yongfeng Zhang. 2021. Causal Collaborative Filtering. arXiv preprint arXiv:2102.01868 (2021)."},{"key":"e_1_3_2_1_49_1","first-page":"14636","article-title":"A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation","volume":"32","author":"Yang Runzhe","year":"2019","unstructured":"Runzhe Yang, Xingyuan Sun, and Karthik Narasimhan. 2019. A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation. Advances in Neural Information Processing Systems , Vol. 32 (2019), 14636--14647.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449901"},{"key":"e_1_3_2_1_51_1","volume-title":"Beyond Parity: Fairness Objectives for Collaborative Filtering. In Advances in Neural Information Processing Systems .","author":"Yao Sirui","year":"2017","unstructured":"Sirui Yao and Bert Huang. 2017. Beyond Parity: Fairness Objectives for Collaborative Filtering. In Advances in Neural Information Processing Systems ."},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of NIPS'17 .","author":"Zafar Muhammad Bilal","year":"2017","unstructured":"Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rodriguez, Krishna P. Gummadi, and Adrian Weller. 2017. From Parity to Preference-Based Notions of Fairness in Classification. In Proceedings of NIPS'17 ."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_1_54_1","volume-title":"Deep Reinforcement Learning for List-wise Recommendations. CoRR","author":"Zhao Xiangyu","year":"2018","unstructured":"Xiangyu Zhao, Liang Zhang, Zhuoye Ding, Dawei Yin, Yihong Zhao, and Jiliang Tang. 2018b. Deep Reinforcement Learning for List-wise Recommendations. CoRR , Vol. abs\/1801.00209 (2018). arxiv: 1801.00209"},{"key":"e_1_3_2_1_55_1","volume-title":"TIK-report","volume":"103","author":"Zitzler Eckart","year":"2001","unstructured":"Eckart Zitzler, Marco Laumanns, and Lothar Thiele. 2001. SPEA2: Improving the strength Pareto evolutionary algorithm. TIK-report , Vol. 103 (2001)."}],"event":{"name":"WSDM '22: The Fifteenth ACM International Conference on Web Search and Data Mining","location":"Virtual Event AZ USA","acronym":"WSDM '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488560.3498487","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3488560.3498487","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:19Z","timestamp":1750188679000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488560.3498487"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,11]]},"references-count":55,"alternative-id":["10.1145\/3488560.3498487","10.1145\/3488560"],"URL":"https:\/\/doi.org\/10.1145\/3488560.3498487","relation":{},"subject":[],"published":{"date-parts":[[2022,2,11]]},"assertion":[{"value":"2022-02-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}