{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:13:33Z","timestamp":1784178813886,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Tencent WeChat Rhino-Bird Focused Research Program"},{"name":"National Natural Science Foundation of China","award":["No. 62006234 No. 61872338 No. 61832017"],"award-info":[{"award-number":["No. 62006234 No. 61872338 No. 61832017"]}]},{"name":"National Key R&D Program of China","award":["2019YFE0198200"],"award-info":[{"award-number":["2019YFE0198200"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,11]]},"DOI":"10.1145\/3404835.3462892","type":"proceedings-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T02:41:48Z","timestamp":1626057708000},"page":"41-50","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":57,"title":["Counterfactual Reward Modification for Streaming Recommendation with Delayed Feedback"],"prefix":"10.1145","author":[{"given":"Xiao","family":"Zhang","sequence":"first","affiliation":[{"name":"Renmin University of China & Beijing Key Laboratory of Big Data Management and Analysis Methods, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haonan","family":"Jia","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Big Data Management and Analysis Methods & Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanjing","family":"Su","sequence":"additional","affiliation":[{"name":"Tencent Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Xu","sequence":"additional","affiliation":[{"name":"Renmin University of China & Beijing Key Laboratory of Big Data Management and Analysis Methods, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji-Rong","family":"Wen","sequence":"additional","affiliation":[{"name":"Renmin University of China & Beijing Key Laboratory of Big Data Management and Analysis Methods, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,7,11]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Unbiased Learning to Rank: Online or Offline? CoRR","author":"Ai Qingyao","year":"2020","unstructured":"Qingyao Ai, Tao Yang, Huazheng Wang, and Jiaxin Mao. 2020. Unbiased Learning to Rank: Online or Offline? CoRR , Vol. abs\/2004.13574 (2020)."},{"key":"e_1_3_2_2_2_1","first-page":"397","article-title":"Using Confidence Bounds for Exploitation-Exploration Trade-offs","volume":"3","author":"Auer Peter","year":"2002","unstructured":"Peter Auer. 2002. Using Confidence Bounds for Exploitation-Exploration Trade-offs. Journal of Machine Learning Research , Vol. 3 (2002), 397--422.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_3_1","unstructured":"Santiago Balseiro Negin Golrezaei Mohammad Mahdian Vahab Mirrokni and Jon Schneider. 2019. Contextual Bandits with Cross-Learning. In Advances in Neural Information Processing Systems 32. 9679--9688."},{"key":"e_1_3_2_2_4_1","volume-title":"Contextual Bandit Algorithms with Supervised Learning Guarantees. In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics","volume":"15","author":"Beygelzimer Alina","unstructured":"Alina Beygelzimer, John Langford, Lihong Li, Lev Reyzin, and Robert E. Schapire. 2011. Contextual Bandit Algorithms with Supervised Learning Guarantees. In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics , Vol. 15. 19--26."},{"key":"e_1_3_2_2_5_1","unstructured":"Ilai Bistritz Zhengyuan Zhou Xi Chen Nicholas Bambos and Jose Blanchet. 2019. Online EXP3 Learning in Adversarial Bandits with Delayed Feedback. In Advances in Neural Information Processing Systems 32. 11349--11358."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/2567709.2567766"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781601986276"},{"key":"e_1_3_2_2_8_1","volume-title":"Proceedings of the ACM SIGMOD International Conference on Management of Data. 1243--1246","author":"Chandramouli Badrish","unstructured":"Badrish Chandramouli, Justin J. Levandoski, Ahmed Eldawy, and Mohamed F. Mokbel. 2011. StreamRec: A Real-time Recommender System. In Proceedings of the ACM SIGMOD International Conference on Management of Data. 1243--1246."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052627"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623634"},{"key":"e_1_3_2_2_11_1","volume-title":"Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. 208--214","author":"Chu Wei","unstructured":"Wei Chu, Lihong Li, Lev Reyzin, and Robert E. Schapire. 2011. Contextual Bandits with Linear Payoff Functions. In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. 208--214."},{"key":"e_1_3_2_2_12_1","unstructured":"Zijun Gao Yanjun Han Zhimei Ren and Zhengqing Zhou. 2019. Batched Multi-armed Bandits Problem. In Advances in Neural Information Processing Systems 32. 501--511."},{"key":"e_1_3_2_2_13_1","volume-title":"Proceedings of the 21st International Conference on Artificial Intelligence and Statistics . 833--842","author":"Grover Aditya","year":"2018","unstructured":"Aditya Grover, Todor M. Markov, Peter M. Attia, Norman Jin, Nicolas Perkins, Bryan Cheong, Michael H. Chen, Zi Yang, Stephen J. Harris, William C. Chueh, and Stefano Ermon. 2018. Best Arm Identification in Multi-armed Bandits with Delayed Feedback. In Proceedings of the 21st International Conference on Artificial Intelligence and Statistics . 833--842."},{"key":"e_1_3_2_2_14_1","volume-title":"Sequential Batch Learning in Finite-Action Linear Contextual Bandits. CoRR","author":"Han Yanjun","year":"2020","unstructured":"Yanjun Han, Zhengqing Zhou, Zhengyuan Zhou, Jose H. Blanchet, Peter W. Glynn, and Yinyu Ye. 2020. Sequential Batch Learning in Finite-Action Linear Contextual Bandits. CoRR , Vol. abs\/2004.06321 (2020)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2648584.2648589"},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning .","author":"Am\u00e9","year":"2020","unstructured":"Am\u00e9 lie H\u00e9 liou, Panayotis Mertikopoulos, and Zhengyuan Zhou. 2020. Gradient-free Online Learning in Games with Delayed Rewards. In Proceedings of the 37th International Conference on Machine Learning ."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331269"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113685"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"J. D. Kalbfleisch and R. L. Prentice. 2002. The Statistical Analysis of Failure Time Data (2nd Edition) .John Wiley & Sons.","DOI":"10.1002\/9781118032985"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.809799"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347002"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210104"},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of the 33rd Conference on Learning Theory. 3049--3068","author":"Neu Gergely","year":"2020","unstructured":"Gergely Neu and Julia Olkhovskaya. 2020. Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits. In Proceedings of the 33rd Conference on Learning Theory. 3049--3068."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1214\/15-AOS1381"},{"key":"e_1_3_2_2_26_1","volume-title":"Off-policy Bandits with Deficient Support. CoRR","author":"Sachdeva Noveen","year":"2020","unstructured":"Noveen Sachdeva, Yi Su, and Thorsten Joachims. 2020. Off-policy Bandits with Deficient Support. CoRR , Vol. abs\/2006.09438 (2020). arxiv: 2006.09438 https:\/\/arxiv.org\/abs\/2006.09438"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401282"},{"key":"e_1_3_2_2_28_1","unstructured":"Eren Sezener Marcus Hutter David Budden Jianan Wang and Joel Veness. 2020. Online Learning in Contextual Bandits using Gated Linear Networks. In Advances in Neural Information Processing Systems 33 ."},{"key":"e_1_3_2_2_29_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning . 6005--6014","author":"Su Yi","year":"2019","unstructured":"Yi Su, Lequn Wang, Michele Santacatterina, and Thorsten Joachims. 2019. CAB: Continuous Adaptive Blending for Policy Evaluation and Learning. In Proceedings of the 36th International Conference on Machine Learning . 6005--6014."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/1314498.1390324"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2886805"},{"key":"e_1_3_2_2_32_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning. 814--823","author":"Swaminathan Adith","year":"2015","unstructured":"Adith Swaminathan and Thorsten Joachims. 2015b. Counterfactual Risk Minimization: Learning from Logged Bandit Feedback. In Proceedings of the 32nd International Conference on Machine Learning. 814--823."},{"key":"e_1_3_2_2_33_1","unstructured":"Adith Swaminathan and Thorsten Joachims. 2015c. The Self-Normalized Estimator for Counterfactual Learning. In Advances in Neural Information Processing Systems 28. 3231--3239."},{"key":"e_1_3_2_2_34_1","volume-title":"Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence .","author":"Vernade Claire","year":"2017","unstructured":"Claire Vernade, Olivier Capp\u00e9 , and Vianney Perchet. 2017. Stochastic Bandit Models for Delayed Conversions. In Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence ."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-008-9056-7"},{"key":"e_1_3_2_2_36_1","volume-title":"Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics . 3848--3857","author":"Wang Chi-Hua","year":"2020","unstructured":"Chi-Hua Wang and Guang Cheng. 2020. Online Batch Decision-Making with High-Dimensional Covariates. In Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics . 3848--3857."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220004"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210016"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133025"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380032"},{"key":"e_1_3_2_2_41_1","volume-title":"A Nonparametric Delayed Feedback Model for Conversion Rate Prediction. arXiv:1802.00255v1","author":"Yoshikawa Yuya","year":"2018","unstructured":"Yuya Yoshikawa and Yusaku Imai. 2018. A Nonparametric Delayed Feedback Model for Conversion Rate Prediction. arXiv:1802.00255v1 (2018)."},{"key":"e_1_3_2_2_42_1","volume-title":"Murphy","author":"Zhang Kelly W.","year":"2020","unstructured":"Kelly W. Zhang, Lucas Janson, and Susan A. Murphy. 2020. Inference for Batched Bandits. In Advances in Neural Information Processing Systems 33 ."},{"key":"e_1_3_2_2_43_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning. 7394--7403","author":"Zhang Xiao","year":"2019","unstructured":"Xiao Zhang and Shizhong Liao. 2019. Incremental Randomized Sketching for Online Kernel Learning. In Proceedings of the 36th International Conference on Machine Learning. 7394--7403."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17305"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45439-5_28"}],"event":{"name":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Virtual Event Canada","acronym":"SIGIR '21","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462892","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404835.3462892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:18Z","timestamp":1750193238000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462892"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":45,"alternative-id":["10.1145\/3404835.3462892","10.1145\/3404835"],"URL":"https:\/\/doi.org\/10.1145\/3404835.3462892","relation":{},"subject":[],"published":{"date-parts":[[2021,7,11]]},"assertion":[{"value":"2021-07-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}