{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T01:33:41Z","timestamp":1768440821406,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761505","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T01:03:42Z","timestamp":1762563822000},"page":"5871-5878","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Stratified Expert Cloning for Retention-Aware Recommendation at Scale"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8049-3989","authenticated-orcid":false,"given":"Chengzhi","family":"Lin","sequence":"first","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8016-9598","authenticated-orcid":false,"given":"Annan","family":"Xie","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1440-911X","authenticated-orcid":false,"given":"Shuchang","family":"Liu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5773-7909","authenticated-orcid":false,"given":"Wuhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2977-9611","authenticated-orcid":false,"given":"Chuyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2153-6722","authenticated-orcid":false,"given":"Yongqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9801-9292","authenticated-orcid":false,"given":"Han","family":"Li","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Mayank Bansal Alex Krizhevsky and Abhijit Ogale. 2018. ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst. showeprintarXiv:1812.03079","DOI":"10.15607\/RSS.2019.XV.031"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3584640"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3584640"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/290941.291025"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608818"},{"key":"e_1_3_2_1_6_1","volume-title":"Kto: Model alignment as prospect theoretic optimization. arXiv preprint arXiv:2402.01306","author":"Ethayarajh Kawin","year":"2024","unstructured":"Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff, Dan Jurafsky, and Douwe Kiela. 2024. Kto: Model alignment as prospect theoretic optimization. arXiv preprint arXiv:2402.01306 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"Conference on Robot Learning. PMLR, 158-168","author":"Florence Pete","year":"2022","unstructured":"Pete Florence, Corey Lynch, Andy Zeng, Oscar A Ramirez, Ayzaan Wahid, Laura Downs, Adrian Wong, Johnny Lee, Igor Mordatch, and Jonathan Tompson. 2022. Implicit behavioral cloning. In Conference on Robot Learning. PMLR, 158-168."},{"key":"e_1_3_2_1_8_1","volume-title":"International conference on machine learning. PMLR, 1587-1596","author":"Fujimoto Scott","year":"2018","unstructured":"Scott Fujimoto, Herke Hoof, and David Meger. 2018. Addressing function approximation error in actor-critic methods. In International conference on machine learning. PMLR, 1587-1596."},{"key":"e_1_3_2_1_9_1","volume-title":"International conference on machine learning. PMLR","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning. PMLR, 1861-1870."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080777"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"e_1_3_2_1_12_1","unstructured":"Bal\u00e1zs Hidasi Alexandros Karatzoglou Linas Baltrunas and Domonkos Tikk. 2015. Session-based Recommendations with Recurrent Neural Networks. showeprintarXiv:1511.06939"},{"key":"e_1_3_2_1_13_1","volume-title":"Generative adversarial imitation learning. Advances in neural information processing systems","author":"Ho Jonathan","year":"2016","unstructured":"Jonathan Ho and Stefano Ermon. 2016. Generative adversarial imitation learning. Advances in neural information processing systems, Vol. 29 (2016)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2903743"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610286"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 2573-2580","author":"Kwon Hyokmin","year":"2020","unstructured":"Hyokmin Kwon, Jaeho Han, and Kyungsik Han. 2020. ART (Attractive Recommendation Tailor) How the Diversity of Product Recommendations Affects Customer Purchase Preference in Fashion Industry?. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 2573-2580."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671531"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","unstructured":"Ziru Liu Shuchang Liu Zijian Zhang Qingpeng Cai Xiangyu Zhao Kesen Zhao Lantao Hu Peng Jiang and Kun Gai. 2024b. Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term Retention. (2024). https:\/\/doi.org\/10.1145\/3626772.3657829 showeprintarXiv:2404.03637","DOI":"10.1145\/3626772.3657829"},{"key":"e_1_3_2_1_20_1","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"Ng Andrew Y","year":"2000","unstructured":"Andrew Y Ng, Stuart Russell, et al., 2000. Algorithms for inverse reinforcement learning.. In Icml, Vol. 1. 2.","journal-title":"Icml"},{"key":"e_1_3_2_1_21_1","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. Advances in neural information processing systems Vol. 35 (2022) 27730-27744."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.2753\/JEC1086-4415180202"},{"key":"e_1_3_2_1_23_1","volume-title":"Efficient training of artificial neural networks for autonomous navigation. Neural computation","author":"Pomerleau Dean A","year":"1991","unstructured":"Dean A Pomerleau. 1991. Efficient training of artificial neural networks for autonomous navigation. Neural computation, Vol. 3, 1 (1991), 88-97."},{"key":"e_1_3_2_1_24_1","volume-title":"Sequence-aware recommender systems. ACM computing surveys (CSUR)","author":"Quadrana Massimo","year":"2018","unstructured":"Massimo Quadrana, Paolo Cremonesi, and Dietmar Jannach. 2018. Sequence-aware recommender systems. ACM computing surveys (CSUR), Vol. 51, 4 (2018), 1-36."},{"key":"e_1_3_2_1_25_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Rafailov Rafael","year":"2024","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2024. Direct preference optimization: Your language model is secretly a reward model. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 627-635","author":"Ross St\u00e9phane","year":"2011","unstructured":"St\u00e9phane Ross, Geoffrey Gordon, and Drew Bagnell. 2011. A reduction of imitation learning and structured prediction to no-regret online learning. In Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 627-635."},{"key":"e_1_3_2_1_27_1","volume-title":"Monte-Carlo simulation, and machine learning.","author":"Rubinstein Reuven Y","unstructured":"Reuven Y Rubinstein and Dirk P Kroese. 2004. The cross-entropy method: a unified approach to combinatorial optimization, Monte-Carlo simulation, and machine learning. Vol. 133. Springer."},{"key":"e_1_3_2_1_28_1","volume-title":"Chinmay Vilas Samak, and Sivanathan Kandhasamy","author":"Samak Tanmay Vilas","year":"2020","unstructured":"Tanmay Vilas Samak, Chinmay Vilas Samak, and Sivanathan Kandhasamy. 2020. Robust behavioral cloning for autonomous vehicles using end-to-end imitation learning. arXiv preprint arXiv:2010.04767 (2020)."},{"key":"e_1_3_2_1_29_1","volume-title":"Andres Carranza, Berivan Isik, Alyssa Unell, Mikail Khona, Thomas Yerxa, Yann LeCun, SueYeon Chung, et al.","author":"Schaeffer Rylan","year":"2024","unstructured":"Rylan Schaeffer, Victor Lecomte, Dhruv Bhandarkar Pai, Andres Carranza, Berivan Isik, Alyssa Unell, Mikail Khona, Thomas Yerxa, Yann LeCun, SueYeon Chung, et al., 2024. Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations. arXiv preprint arXiv:2406.09366 (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.06.026"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331210"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331224"},{"key":"e_1_3_2_1_33_1","volume-title":"Behavioral Cloning Models Reality Check for Autonomous Driving. arXiv preprint arXiv:2409.07218","author":"Yildirim Mustafa","year":"2024","unstructured":"Mustafa Yildirim, Barkin Dagda, Vinal Asodia, and Saber Fallah. 2024. Behavioral Cloning Models Reality Check for Autonomous Driving. arXiv preprint arXiv:2409.07218 (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"A survey of imitation learning: Algorithms, recent developments, and challenges","author":"Zare Maryam","year":"2024","unstructured":"Maryam Zare, Parham M Kebria, Abbas Khosravi, and Saeid Nahavandi. 2024. A survey of imitation learning: Algorithms, recent developments, and challenges. IEEE Transactions on Cybernetics (2024)."},{"key":"e_1_3_2_1_35_1","first-page":"44880","article-title":"KuaiSim: A comprehensive simulator for recommender systems","volume":"36","author":"Zhao Kesen","year":"2023","unstructured":"Kesen Zhao, Shuchang Liu, Qingpeng Cai, Xiangyu Zhao, Ziru Liu, Dong Zheng, Peng Jiang, and Kun Gai. 2023a. KuaiSim: A comprehensive simulator for recommender systems. Advances in Neural Information Processing Systems, Vol. 36 (2023), 44880-44897.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583418"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T15:27:19Z","timestamp":1768404439000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":37,"alternative-id":["10.1145\/3746252.3761505","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761505","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}