{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T05:30:39Z","timestamp":1762061439550,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"MOST of Taiwan","award":["110-2221-E-002-115-MY3"],"award-info":[{"award-number":["110-2221-E-002-115-MY3"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539295","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:41Z","timestamp":1660331201000},"page":"1141-1151","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Practical Counterfactual Policy Learning for Top-K Recommendations"],"prefix":"10.1145","author":[{"given":"Yaxu","family":"Liu","sequence":"first","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jui-Nan","family":"Yen","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowen","family":"Yuan","sequence":"additional","affiliation":[{"name":"Amazon, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rundong","family":"Shi","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Yan","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chih-Jen","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics. 17--24","author":"Bengio Yoshua","year":"2003","unstructured":"Yoshua Bengio and Jean-S\u00e9bastien Sen\u00e9cal. 2003. Quick Training of Probabilistic Neural Nets by Importance Sampling. In Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics. 17--24."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"volume-title":"Proceedings of the 14th ACM International Conference on Web Search and Data Mining (WSDM). 121--129","author":"Chen Minmin","key":"e_1_3_2_2_3_1","unstructured":"Minmin Chen, Bo Chang, Can Xu, and Ed H. Chi. 2021. User Response Models to Improve a REINFORCE Recommender System. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining (WSDM). 121--129."},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the 28th International Conference on International Conference on Machine Learning (ICML). 1097--1104","author":"Dud\u00edk Miroslav","year":"2011","unstructured":"Miroslav Dud\u00edk, John Langford, and Lihong Li. 2011. Doubly Robust Policy Evaluation and Learning. In Proceedings of the 28th International Conference on International Conference on Machine Learning (ICML). 1097--1104."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1952.10483446"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/1248547.1248551"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403175"},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Joachims Thorsten","year":"2018","unstructured":"Thorsten Joachims, Adith Swaminathan, and Maarten de Rijke. 2018. Deep learning with logged bandit feedback. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_2_11_1","volume-title":"NIPS Workshop on Inference and Learning of Hypothetical and Counterfactual Interventions in Complex Systems.","author":"Lefortier Damien","year":"2016","unstructured":"Damien Lefortier, Adith Swaminathan, Xiaotao Gu, Thorsten Joachims, and Maarten de Rijke. 2016. Large-scale validation of counterfactual learning methods: A test-bed. In NIPS Workshop on Inference and Learning of Hypothetical and Counterfactual Interventions in Complex Systems."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220028"},{"key":"e_1_3_2_2_13_1","volume-title":"Jordan","author":"Lopez Romain","year":"2021","unstructured":"Romain Lopez, Inderjit Dhillon, and Michael I. Jordan. 2021. Learning from eXtreme Bandit Feedback. (2021)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380130"},{"volume-title":"Analyzing and Modeling Rank Data","author":"Marden John I.","key":"e_1_3_2_2_15_1","unstructured":"John I. Marden. 1995. Analyzing and Modeling Rank Data. Chapman & Hall, London."},{"volume-title":"Proceedings of the Seventeenth International Conference on Machine Learning (ICML). 759--766","author":"Precup Doina","key":"e_1_3_2_2_16_1","unstructured":"Doina Precup, Richard S. Sutton, and Satinder P. Singh. 2000. Eligibility Traces for Off-Policy Policy Evaluation. In Proceedings of the Seventeenth International Conference on Machine Learning (ICML). 759--766."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403139"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2886805"},{"key":"e_1_3_2_2_20_1","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS). 3231--3239","author":"Swaminathan Adith","year":"2015","unstructured":"Adith Swaminathan and Thorsten Joachims. 2015. The Self-normalized Estimator for Counterfactual Learning. In Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS). 3231--3239."},{"key":"e_1_3_2_2_21_1","unstructured":"Adith Swaminathan Akshay Krishnamurthy Alekh Agarwal Miroslav Dud\u00edk John Langford Damien Jose and Imed Zitouni. 2017. Off-Policy Evaluation for Slate Recommendation. (2017) 3635--3645."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346996"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974973.41"},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI). http:\/\/www.csie.ntu.edu.tw\/~cjlin\/papers\/ocmf-side\/biasedleml-aaai-with-supp.pdf","author":"Yu Hsiang-Fu","year":"2017","unstructured":"Hsiang-Fu Yu, Hsin-Yuan Huang, Inderjit S. Dihillon, and Chih-Jen Lin. 2017. A Unified Algorithm for One-class Structured Matrix Factorization with Side Information. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI). http:\/\/www.csie.ntu.edu.tw\/~cjlin\/papers\/ocmf-side\/biasedleml-aaai-with-supp.pdf"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358058"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467363"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412241"}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Washington DC USA","acronym":"KDD '22"},"container-title":["Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539295","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:59:59Z","timestamp":1750186799000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539295"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":27,"alternative-id":["10.1145\/3534678.3539295","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539295","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}