{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T16:48:22Z","timestamp":1755794902147,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":39,"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"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20253"],"award-info":[{"award-number":["U24A20253"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709169","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:42:22Z","timestamp":1743792142000},"page":"1127-1137","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Understanding the Effect of Loss Functions on the Generalization of Recommendations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9485-5573","authenticated-orcid":false,"given":"Yuanhao","family":"Pu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China and State Key Laboratory of Cognitive Intelligence, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3507-9607","authenticated-orcid":false,"given":"Defu","family":"Lian","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China and State Key Laboratory of Cognitive Intelligence, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2714-6404","authenticated-orcid":false,"given":"Xiaolong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China and State Key Laboratory of Cognitive Intelligence, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6440-2242","authenticated-orcid":false,"given":"Jin","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5208-8908","authenticated-orcid":false,"given":"Ze","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China and State Key Laboratory of Cognitive Intelligence, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4835-4102","authenticated-orcid":false,"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China and State Key Laboratory of Cognitive Intelligence, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_2_1_1","first-page":"9804","article-title":"Calibration and consistency of adversarial surrogate losses","volume":"34","author":"Awasthi Pranjal","year":"2021","unstructured":"Pranjal Awasthi, Natalie Frank, Anqi Mao, Mehryar Mohri, and Yutao Zhong. 2021. Calibration and consistency of adversarial surrogate losses. Advances in Neural Information Processing Systems, Vol. 34 (2021), 9804--9815.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_2_1","volume-title":"International Conference on Machine Learning. PMLR, 1117--1174","author":"Awasthi Pranjal","year":"2022","unstructured":"Pranjal Awasthi, Anqi Mao, Mehryar Mohri, and Yutao Zhong. 2022a. H-consistency bounds for surrogate loss minimizers. In International Conference on Machine Learning. PMLR, 1117--1174."},{"key":"e_1_3_2_2_3_1","volume-title":"Advances in neural information processing systems","author":"Awasthi Pranjal","year":"2022","unstructured":"Pranjal Awasthi, Anqi Mao, Mehryar Mohri, and Yutao Zhong. 2022b. Multi-Class H -Consistency Bounds. Advances in neural information processing systems, Vol. 35 (2022), 782--795."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1198\/016214505000000907"},{"key":"e_1_3_2_2_5_1","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Cortes Corinna","year":"2016","unstructured":"Corinna Cortes, Giulia DeSalvo, and Mehryar Mohri. 2016a. Boosting with abstention. Advances in Neural Information Processing Systems, Vol. 29 (2016)."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46379-7_5"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330651"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_2_12_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"volume-title":"International Conference on Learning Representations.","author":"Krichene Walid","key":"e_1_3_2_2_13_1","unstructured":"Walid Krichene, Nicolas Mayoraz, Steffen Rendle, Li Zhang, Xinyang Yi, Lichan Hong, Ed Chi, and John Anderson. [n.,d.]. Efficient Training on Very Large Corpora via Gramian Estimation. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_14_1","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Kuznetsov Vitaly","year":"2014","unstructured":"Vitaly Kuznetsov, Mehryar Mohri, and Umar Syed. 2014. Multi-class deep boosting. Advances in Neural Information Processing Systems, Vol. 27 (2014)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557072"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591894"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380151"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403252"},{"key":"e_1_3_2_2_19_1","volume-title":"International conference on machine learning. PMLR, 801--809","author":"Long Phil","year":"2013","unstructured":"Phil Long and Rocco Servedio. 2013. Consistency versus realizable H-consistency for multiclass classification. In International conference on machine learning. PMLR, 801--809."},{"key":"e_1_3_2_2_20_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Mao Anqi","year":"2024","unstructured":"Anqi Mao, Mehryar Mohri, and Yutao Zhong. 2024a. H -Consistency Bounds: Characterization and Extensions. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_21_1","volume-title":"arXiv preprint arXiv:2407.13722","author":"Mao Anqi","year":"2024","unstructured":"Anqi Mao, Mehryar Mohri, and Yutao Zhong. 2024b. Enhanced H -Consistency Bounds. arXiv preprint arXiv:2407.13722 (2024)."},{"key":"e_1_3_2_2_22_1","volume-title":"Top- k Classification and Cardinality-Aware Prediction. arXiv preprint arXiv:2403.19625","author":"Mao Anqi","year":"2024","unstructured":"Anqi Mao, Mehryar Mohri, and Yutao Zhong. 2024c. Top- k Classification and Cardinality-Aware Prediction. arXiv preprint arXiv:2403.19625 (2024)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482297"},{"key":"e_1_3_2_2_24_1","volume-title":"Sashank Reddi, and Sanjiv Kumar.","author":"Menon Aditya K","year":"2019","unstructured":"Aditya K Menon, Ankit Singh Rawat, Sashank Reddi, and Sanjiv Kumar. 2019. Multilabel reductions: what is my loss optimising? Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/3692070.3693743"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462864"},{"key":"e_1_3_2_2_27_1","volume-title":"BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618","author":"Rendle Steffen","year":"2012","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2012. BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618 (2012)."},{"key":"e_1_3_2_2_28_1","article-title":"On the Consistency of Multiclass Classification Methods","volume":"8","author":"Tewari Ambuj","year":"2007","unstructured":"Ambuj Tewari and Peter L Bartlett. 2007. On the Consistency of Multiclass Classification Methods. Journal of Machine Learning Research, Vol. 8, 5 (2007).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018689"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00068"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637061"},{"key":"e_1_3_2_2_32_1","volume-title":"A no-regret generalization of hierarchical softmax to extreme multi-label classification. Advances in neural information processing systems","author":"Wydmuch Marek","year":"2018","unstructured":"Marek Wydmuch, Kalina Jasinska, Mikhail Kuznetsov, R\u00f3bert Busa-Fekete, and Krzysztof Dembczynski. 2018. A no-regret generalization of hierarchical softmax to extreme multi-label classification. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_2_33_1","volume-title":"Zhiming Cui, Xiaofang Zhou, and Hui Xiong.","author":"Xu Chengfeng","year":"2019","unstructured":"Chengfeng Xu, Pengpeng Zhao, Yanchi Liu, Jiajie Xu, Victor S Sheng S. Sheng, Zhiming Cui, Xiaofang Zhou, and Hui Xiong. 2019. Recurrent convolutional neural network for sequential recommendation. In The world wide web conference. 3398--3404."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346996"},{"key":"e_1_3_2_2_35_1","volume-title":"A dual augmented two-tower model for online large-scale recommendation. DLP-KDD","author":"Yu Yantao","year":"2021","unstructured":"Yantao Yu, Weipeng Wang, Zhoutian Feng, and Daiyue Xue. 2021. A dual augmented two-tower model for online large-scale recommendation. DLP-KDD (2021)."},{"volume-title":"Forty-first International Conference on Machine Learning.","author":"Zhai Jiaqi","key":"e_1_3_2_2_36_1","unstructured":"Jiaqi Zhai, Lucy Liao, Xing Liu, Yueming Wang, Rui Li, Xuan Cao, Leon Gao, Zhaojie Gong, Fangda Gu, Jiayuan He, et al. [n.,d.]. Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_2_37_1","volume-title":"Bayes consistency vs. H-consistency: The interplay between surrogate loss functions and the scoring function class. Advances in neural information processing systems","author":"Zhang Mingyuan","year":"2020","unstructured":"Mingyuan Zhang and Shivani Agarwal. 2020. Bayes consistency vs. H-consistency: The interplay between surrogate loss functions and the scoring function class. Advances in neural information processing systems, Vol. 33 (2020), 16927--16936."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/1005332.1044701"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1079120130"}],"event":{"name":"KDD '25: The 31st 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":"Toronto ON Canada","acronym":"KDD '25"},"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\/3690624.3709169","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:38:06Z","timestamp":1755358686000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709169"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":39,"alternative-id":["10.1145\/3690624.3709169","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709169","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"}}]}}