{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:39:23Z","timestamp":1786120763698,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"IBM-Illinois Discovery Accelerator Institute","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817809","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:43Z","timestamp":1786036543000},"page":"4000-4011","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Generalizable Multi-Pass Training of Ads Recommendation Models with Foundation Model Guidance"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5828-7436","authenticated-orcid":false,"given":"Yunzhe","family":"Qi","sequence":"first","affiliation":[{"name":"UIUC, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2571-5796","authenticated-orcid":false,"given":"Qinghai","family":"Zhou","sequence":"additional","affiliation":[{"name":"Meta Platforms, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2540-0712","authenticated-orcid":false,"given":"Boyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta Platforms, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2159-5387","authenticated-orcid":false,"given":"Can","family":"Cui","sequence":"additional","affiliation":[{"name":"Meta Platforms, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9555-7132","authenticated-orcid":false,"given":"Hua","family":"Zheng","sequence":"additional","affiliation":[{"name":"Meta Platforms, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8072-6060","authenticated-orcid":false,"given":"Qiuling","family":"Suo","sequence":"additional","affiliation":[{"name":"Meta Platforms, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6779-2418","authenticated-orcid":false,"given":"Mingfu","family":"Liang","sequence":"additional","affiliation":[{"name":"Meta Platforms, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4260-9633","authenticated-orcid":false,"given":"Kenny","family":"Lov","sequence":"additional","affiliation":[{"name":"Meta Platforms, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2336-8417","authenticated-orcid":false,"given":"Xi","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta Platforms, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7999-6029","authenticated-orcid":false,"given":"Shali","family":"Jiang","sequence":"additional","affiliation":[{"name":"Meta Platforms, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6384-3810","authenticated-orcid":false,"given":"Laming","family":"Chen","sequence":"additional","affiliation":[{"name":"Meta Platforms, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9371-5642","authenticated-orcid":false,"given":"Wen-Yen","family":"Chen","sequence":"additional","affiliation":[{"name":"Meta Platforms, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8797-4646","authenticated-orcid":false,"given":"Rong","family":"Jin","sequence":"additional","affiliation":[{"name":"Meta Platforms, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8016-9506","authenticated-orcid":false,"given":"Shuo","family":"Chang","sequence":"additional","affiliation":[{"name":"Meta Platforms, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6429-6272","authenticated-orcid":false,"given":"Jingrui","family":"He","sequence":"additional","affiliation":[{"name":"UIUC, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7855-3522","authenticated-orcid":false,"given":"Huayu","family":"Li","sequence":"additional","affiliation":[{"name":"Meta Platforms, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Deep Variational Information Bottleneck. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=HyxQzBceg","author":"Alemi Alexander A.","year":"2017","unstructured":"Alexander A. Alemi, Ian Fischer, Joshua V. Dillon, and Kevin Murphy. 2017. Deep Variational Information Bottleneck. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=HyxQzBceg"},{"key":"e_1_3_2_1_2_1","volume-title":"V5, 4","author":"Chapelle Olivier","year":"2014","unstructured":"Olivier Chapelle, Eren Manavoglu, and Romer Rosales. 2014. Simple and scalable response prediction for display advertising. ACM Transactions on Intelligent Systems and Technology (TIST), V5, 4 (2014), 1-34."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326937.3341261"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML) (Proceedings of Machine Learning Research","volume":"1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the 37th International Conference on Machine Learning (ICML) (Proceedings of Machine Learning Research, Vol. V119). PMLR, 1597-1607."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240617"},{"key":"e_1_3_2_1_6_1","volume-title":"International conference on machine learning. PMLR, 794-803","author":"Chen Zhao","year":"2018","unstructured":"Zhao Chen, Vijay Badrinarayanan, Chen-Yu Lee, and Andrew Rabinovich. 2018a. Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In International conference on machine learning. PMLR, 794-803."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_9_1","unstructured":"Yewen Fan Nian Si and Kun Zhang. 2023. Calibration Matters: Tackling Maximization Bias in Large-scale Advertising Recommendation Systems. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=wzlWiO_WY4"},{"key":"e_1_3_2_1_10_1","volume-title":"Multi-Epoch learning with Data Augmentation for Deep Click-Through Rate Prediction. arXiv preprint arXiv:2407.01607","author":"Fan Zhongxiang","year":"2024","unstructured":"Zhongxiang Fan, Zhaocheng Liu, Jian Liang, Dongying Kong, Han Li, Peng Jiang, Shuang Li, and Kun Gai. 2024. Multi-Epoch learning with Data Augmentation for Deep Click-Through Rate Prediction. arXiv preprint arXiv:2407.01607 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. PMLR, 1568-1577","author":"Franceschi Luca","year":"2018","unstructured":"Luca Franceschi, Paolo Frasconi, Saverio Salzo, Riccardo Grazzi, and Massimiliano Pontil. 2018. Bilevel programming for hyperparameter optimization and meta-learning. In International conference on machine learning. PMLR, 1568-1577."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1198\/016214506000001437"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/239"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2648584.2648589"},{"key":"e_1_3_2_1_15_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_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688053"},{"key":"e_1_3_2_1_17_1","volume-title":"Foundation models for recommender systems: A survey and new perspectives. arXiv preprint arXiv:2402.11143","author":"Huang Chengkai","year":"2024","unstructured":"Chengkai Huang, Tong Yu, Kaige Xie, Shuai Zhang, Lina Yao, and Julian McAuley. 2024. Foundation models for recommender systems: A survey and new perspectives. arXiv preprint arXiv:2402.11143 (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"International conference on machine learning. PMLR, 4882-4892","author":"Ji Kaiyi","year":"2021","unstructured":"Kaiyi Ji, Junjie Yang, and Yingbin Liang. 2021. Bilevel optimization: Convergence analysis and enhanced design. In International conference on machine learning. PMLR, 4882-4892."},{"key":"e_1_3_2_1_19_1","unstructured":"Shali Jiang Hua Zheng Boyang Liu Laming Chen Kenny Lov Chuanqi Xu Lisang Ding Qinghai Zhou Can Cui Xiaolong Liu et al. 2026. LoopFM: Learning frOm HistOrical RePresentations of Foundation Model for Recommendation. arXiv preprint arXiv:2605.29280 (2026)."},{"key":"e_1_3_2_1_20_1","volume-title":"V193","author":"Jose Aljo","year":"2022","unstructured":"Aljo Jose and Sujala D Shetty. 2022. DistilledCTR: Accurate and scalable CTR prediction model through model distillation. Expert Systems with Applications, V193 (2022), 116474."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 7482-7491","author":"Kendall Alex","year":"2018","unstructured":"Alex Kendall, Yarin Gal, and Roberto Cipolla. 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7482-7491."},{"key":"e_1_3_2_1_22_1","volume-title":"V36","author":"Kuang Huafeng","year":"2023","unstructured":"Huafeng Kuang, Hong Liu, Yongjian Wu, Shin'ichi Satoh, and Rongrong Ji. 2023. Improving adversarial robustness via information bottleneck distillation. Advances in Neural Information Processing Systems, V36 (2023), 10796-10813."},{"key":"e_1_3_2_1_23_1","volume-title":"Adaptive Regularization for Large-Scale Sparse Feature Embedding Models. In The Fourteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=QFH5mwP9oH","author":"Li Mang","year":"2026","unstructured":"Mang Li and Wei Lyu. 2026. Adaptive Regularization for Large-Scale Sparse Feature Embedding Models. In The Fourteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=QFH5mwP9oH"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350950"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715223"},{"key":"e_1_3_2_1_26_1","unstructured":"Zhaocheng Liu Zhongxiang Fan Jian Liang Dongying Kong and Han Li. 2023. Multi-Epoch Learning for Deep Click-Through Rate Prediction Models. CoRR (OpenReview preprint). https:\/\/openreview.net\/forum?id=OHml9bbfnl Last modified: 2025-02-06."},{"key":"e_1_3_2_1_27_1","first-page":"2579","article-title":"Visualizing data using t-SNE","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, V9, Nov (2008), 2579-2605.","journal-title":"Journal of machine learning research, V9"},{"key":"e_1_3_2_1_28_1","first-page":"1","article-title":"The benefit of multitask representation learning","volume":"17","author":"Maurer Andreas","year":"2016","unstructured":"Andreas Maurer, Massimiliano Pontil, and Bernardino Romera-Paredes. 2016. The benefit of multitask representation learning. Journal of Machine Learning Research, V17, 81 (2016), 1-32.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2488200"},{"key":"e_1_3_2_1_30_1","volume-title":"Foundations of machine learning","author":"Mohri Mehryar","unstructured":"Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar. 2018. Foundations of machine learning. MIT press."},{"key":"e_1_3_2_1_31_1","volume-title":"Jianyu Huang, Narayanan Sundaraman, Jongsoo Park, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Alisson G Azzolini, et al.","author":"Naumov Maxim","year":"2019","unstructured":"Maxim Naumov, Dheevatsa Mudigere, Hao-Jun Michael Shi, Jianyu Huang, Narayanan Sundaraman, Jongsoo Park, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Alisson G Azzolini, et al., 2019. Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091 (2019)."},{"key":"e_1_3_2_1_32_1","volume-title":"International conference on machine learning. PMLR, 5171-5180","author":"Poole Ben","year":"2019","unstructured":"Ben Poole, Sherjil Ozair, Aaron Van Den Oord, Alex Alemi, and George Tucker. 2019. On variational bounds of mutual information. In International conference on machine learning. PMLR, 5171-5180."},{"key":"e_1_3_2_1_33_1","volume-title":"Runze Su, Rafael Rios M\u00fcller, Kungang Li, Ling Leng, Han Sun, Shayan Ehsani, and Zhifang Liu.","author":"Qiu Andrew","year":"2025","unstructured":"Andrew Qiu, Shubham Barhate, Hin Wai Lui, Runze Su, Rafael Rios M\u00fcller, Kungang Li, Ling Leng, Han Sun, Shayan Ehsani, and Zhifang Liu. 2025. The Evolution of Embedding Table Optimization and Multi-Epoch Training in Pinterest Ads Conversion. arXiv preprint arXiv:2505.05605 (2025)."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML) (Proceedings of Machine Learning Research","volume":"8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning (ICML) (Proceedings of Machine Learning Research, Vol. V139). PMLR, 8748-8763."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3705328.3748138"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242643"},{"key":"e_1_3_2_1_38_1","volume-title":"An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098","author":"Ruder Sebastian","year":"2017","unstructured":"Sebastian Ruder. 2017. An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098 (2017)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/2621980"},{"key":"e_1_3_2_1_40_1","volume-title":"Contrastive Representation Distillation. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SkgpBJrtvS","author":"Tian Yonglong","year":"2020","unstructured":"Yonglong Tian, Dilip Krishnan, and Phillip Isola. 2020. Contrastive Representation Distillation. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SkgpBJrtvS"},{"key":"e_1_3_2_1_41_1","volume-title":"Representation Learning with Contrastive Predictive Coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation Learning with Contrastive Predictive Coding. arXiv preprint arXiv:1807.03748 (2018). arXiv:1807.03748"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450078"},{"key":"e_1_3_2_1_44_1","volume-title":"International conference on machine learning. PMLR, 9929-9939","author":"Wang Tongzhou","year":"2020","unstructured":"Tongzhou Wang and Phillip Isola. 2020. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In International conference on machine learning. PMLR, 9929-9939."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412092"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761527"},{"key":"e_1_3_2_1_47_1","volume-title":"International Conference on Machine Learning. PMLR, 59421-59434","author":"Zhang Buyun","year":"2024","unstructured":"Buyun Zhang, Liang Luo, Yuxin Chen, Jade Nie, Xi Liu, Shen Li, Yanli Zhao, Yuchen Hao, Yantao Yao, Ellie Dingqiao Wen, et al., 2024. Wukong: Towards a Scaling Law for Large-Scale Recommendation. In International Conference on Machine Learning. PMLR, 59421-59434."},{"key":"e_1_3_2_1_48_1","volume-title":"DHEN: A deep and hierarchical ensemble network for large-scale click-through rate prediction. arXiv preprint arXiv:2203.11014","author":"Zhang Buyun","year":"2022","unstructured":"Buyun Zhang, Liang Luo, Xi Liu, Jay Li, Zeliang Chen, Weilin Zhang, Xiaohan Wei, Yuchen Hao, Michael Tsang, Wenjun Wang, et al., 2022a. DHEN: A deep and hierarchical ensemble network for large-scale click-through rate prediction. arXiv preprint arXiv:2203.11014 (2022)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557479"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015941"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531723"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482486"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:30:31Z","timestamp":1786066231000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817809"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":53,"alternative-id":["10.1145\/3770855.3817809","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817809","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}