{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:43:15Z","timestamp":1783701795257,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"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":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709403","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:42:22Z","timestamp":1743792142000},"page":"2725-2734","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Mutual Information-aware Knowledge Distillation for Short Video Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3264-1226","authenticated-orcid":false,"given":"Han","family":"Xu","sequence":"first","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1577-0200","authenticated-orcid":false,"given":"Taoxing","family":"Pan","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1143-9340","authenticated-orcid":false,"given":"Zhiqiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5493-5628","authenticated-orcid":false,"given":"Xiaoxiao","family":"Xu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3209986"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.1979.308793"},{"key":"e_1_3_2_2_3_1","volume-title":"Proceedings, Part VI. 548--564","author":"Boudiaf Malik","year":"2020","unstructured":"Malik Boudiaf, J\u00e9r\u00f4me Rony, Imtiaz Masud Ziko, Eric Granger, Marco Pedersoli, Pablo Piantanida, and Ismail Ben Ayed. 2020. A Unifying Mutual Information View of Metric Learning: Cross-Entropy vs. Pairwise Losses. In Computer Vision -- ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part VI. 548--564."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583259"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2016.2637439"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_2_7_1","volume-title":"Adaptive Subgradient Methods for Online Learning and Stochastic Optimization. Journal of Machine Learning Research","author":"Duchi John","year":"2011","unstructured":"John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive Subgradient Methods for Online Learning and Stochastic Optimization. Journal of Machine Learning Research (2011), 2121--2159."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498478"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90003-8"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557624"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635810"},{"key":"e_1_3_2_2_12_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347033"},{"key":"e_1_3_2_2_14_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2433396.2433419"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463117"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347043"},{"key":"e_1_3_2_2_18_1","unstructured":"Xiang Li Shuwei Chen Jian Dong Jin Zhang Yongkang Wang Xingxing Wang and Dong Wang. 2023. Decision-Making Context Interaction Network for Click-through Rate Prediction. In Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence."},{"key":"e_1_3_2_2_19_1","volume-title":"Tree based Progressive Regression Model for Watch-Time Prediction in Short-video Recommendation. arXiv preprint arXiv:2306.03392","author":"Lin Xiao","year":"2023","unstructured":"Xiao Lin, Xiaokai Chen, Linfeng Song, Jingwei Liu, Biao Li, and Peng Jiang. 2023. Tree based Progressive Regression Model for Watch-Time Prediction in Short-video Recommendation. arXiv preprint arXiv:2306.03392 (2023)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3617826"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2886805"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599797"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911537"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159732"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3745"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403309"},{"key":"e_1_3_2_2_28_1","unstructured":"Han Xu Taoxing Pan Zhiqiang Liu Xiaoxiao Xu and Lantao Lu. 2024. Incorporating Group Prior into Variational Inference for Tail-User Behavior Modeling in CTR Prediction. arxiv: 2410.15098"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"crossref","unstructured":"Han Xu Hao Qi Yaokun Wang Pei Wang Guowei Zhang Congcong Liu Junsheng Jin Xiwei Zhao Zhangang Lin Jinghe Hu and Jingping Shao. 2023. PCDF: A Parallel-Computing Distributed Framework for Sponsored Search Advertising Serving. In Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track: European Conference ECML PKDD 2023.","DOI":"10.1007\/978-3-031-43427-3_40"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512048"},{"key":"e_1_3_2_2_31_1","first-page":"26658","article-title":"Toward Understanding Privileged Features Distillation in Learning-to-Rank","volume":"35","author":"Yang Shuo","year":"2022","unstructured":"Shuo Yang, Sujay Sanghavi, Holakou Rahmanian, Jan Bakus, and Vishwanathan SVN. 2022. Toward Understanding Privileged Features Distillation in Learning-to-Rank. Advances in Neural Information Processing Systems, Vol. 35 (2022), 26658--26670.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539092"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346997"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015941"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709403","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:34:26Z","timestamp":1755358466000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709403"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":35,"alternative-id":["10.1145\/3690624.3709403","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709403","relation":{},"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"2025-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}