{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T16:48:30Z","timestamp":1755794910789,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":47,"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\/3690624.3709182","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:44:43Z","timestamp":1743792283000},"page":"1161-1172","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Adapting to Generalized Online Label Shift by Invariant Representation Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5812-2807","authenticated-orcid":false,"given":"Yu-Yang","family":"Qian","sequence":"first","affiliation":[{"name":"National Key Laboratory for Novel Software Technology & School of Artificial Intelligence, Nanjing University, Nanjing, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5220-4024","authenticated-orcid":false,"given":"Yi-Han","family":"Wang","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology & School of Artificial Intelligence, Nanjing University, Nanjing, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2101-1836","authenticated-orcid":false,"given":"Zhen-Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Center for Advanced Intelligence Project, RIKEN, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8093-4826","authenticated-orcid":false,"given":"Yuan","family":"Jiang","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology & School of Artificial Intelligence, Nanjing University, Nanjing, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0746-1494","authenticated-orcid":false,"given":"Zhi-Hua","family":"Zhou","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology & School of Artificial Intelligence, Nanjing University, Nanjing, Jiangsu, China"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Invariant Risk Minimization. ArXiv preprint","author":"Arjovsky Mart\u00edn","year":"2019","unstructured":"Mart\u00edn Arjovsky, L\u00e9on Bottou, Ishaan Gulrajani, and David Lopez-Paz. 2019. Invariant Risk Minimization. ArXiv preprint, Vol. arXiv:1907.02893 (2019)."},{"key":"e_1_3_2_2_2_1","volume-title":"Zachary Chase Lipton, and Yu-Xiang Wang","author":"Baby Dheeraj","year":"2023","unstructured":"Dheeraj Baby, Saurabh Garg, Tzu-Ching Yen, Sivaraman Balakrishnan, Zachary Chase Lipton, and Yu-Xiang Wang. 2023. Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms. In Advances in Neural Information Processing Systems 36 (NeurIPS). 65703--65742."},{"key":"e_1_3_2_2_3_1","unstructured":"Yong Bai Yu-Jie Zhang Peng Zhao Masashi Sugiyama and Zhi-Hua Zhou. 2022. Adapting to Online Label Shift with Provable Guarantees. In Advances in Neural Information Processing Systems 35 (NeurIPS). 29960--29974."},{"key":"e_1_3_2_2_4_1","volume-title":"The iWildCam 2020 Competition Dataset. ArXiv preprint","author":"Beery Sara","year":"2020","unstructured":"Sara Beery, Elijah Cole, and Arvi Gjoka. 2020. The iWildCam 2020 Competition Dataset. ArXiv preprint, Vol. arXiv:2004.10340 (2020)."},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS). 8299--8339","author":"Bisla Devansh","year":"2022","unstructured":"Devansh Bisla, Jing Wang, and Anna Choromanska. 2022. Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape. In Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS). 8299--8339."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00816"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16861"},{"key":"e_1_3_2_2_8_1","volume-title":"Proceedings of the 7th International Conference on Learning Representations (ICLR).","author":"Chaudhry Arslan","year":"2019","unstructured":"Arslan Chaudhry, Marc'Aurelio Ranzato, Marcus Rohrbach, and Mohamed Elhoseiny. 2019. Efficient Lifelong Learning with A-GEM. In Proceedings of the 7th International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML). 6643--6670","author":"Cutkosky Ashok","year":"2023","unstructured":"Ashok Cutkosky, Harsh Mehta, and Francesco Orabona. 2023. Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion. In Proceedings of the 40th International Conference on Machine Learning (ICML). 6643--6670."},{"key":"e_1_3_2_2_10_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML). 1405--1411","author":"Daniely Amit","year":"2015","unstructured":"Amit Daniely, Alon Gonen, and Shai Shalev-Shwartz. 2015. Strongly Adaptive Online Learning. In Proceedings of the 32nd International Conference on Machine Learning (ICML). 1405--1411."},{"key":"e_1_3_2_2_11_1","volume-title":"Swati Padmanabhan, and Guanghao Ye.","author":"Davis Damek","year":"2022","unstructured":"Damek Davis, Dmitriy Drusvyatskiy, Yin Tat Lee, Swati Padmanabhan, and Guanghao Ye. 2022. A gradient sampling method with complexity guarantees for Lipschitz functions in high and low dimensions. In Advances in Neural Information Processing Systems 35 (NeurIPS). 6692--6703."},{"key":"e_1_3_2_2_12_1","volume-title":"Gordon","author":"des Combes Remi Tachet","year":"2020","unstructured":"Remi Tachet des Combes, Han Zhao, Yu-Xiang Wang, and Geoffrey J. Gordon. 2020. Domain adaptation with conditional distribution matching and generalized label shift. In Advances in Neural Information Processing Systems 33 (NeurIPS). 19276--19289."},{"key":"e_1_3_2_2_13_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML). 1126--1135","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. In Proceedings of the 34th International Conference on Machine Learning (ICML). 1126--1135."},{"key":"e_1_3_2_2_14_1","volume-title":"Online Meta-Learning. In Proceedings of the 36th International Conference on Machine Learning (ICML). 1920--1930","author":"Finn Chelsea","year":"2019","unstructured":"Chelsea Finn, Aravind Rajeswaran, Sham Kakade, and Sergey Levine. 2019. Online Meta-Learning. In Proceedings of the 36th International Conference on Machine Learning (ICML). 1920--1930."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403214"},{"key":"e_1_3_2_2_16_1","first-page":"5149","article-title":"Meta-Learning in Neural Networks: A Survey","volume":"44","author":"Hospedales Timothy","year":"2022","unstructured":"Timothy Hospedales, Antreas Antoniou, Paul Micaelli, and Amos Storkey. 2022. Meta-Learning in Neural Networks: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 9 (2022), 5149--5169.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"volume-title":"Proceedings of the 39th International Conference on Machine Learning (ICML). 10734--10750","author":"Kang Haeyong","key":"e_1_3_2_2_17_1","unstructured":"Haeyong Kang, Rusty John Lloyd Mina, Sultan Rizky Hikmawan Madjid, Jaehong Yoon, Mark Hasegawa-Johnson, Sung Ju Hwang, and Chang D. Yoo. 2022. Forget-free Continual Learning with Winning Subnetworks. In Proceedings of the 39th International Conference on Machine Learning (ICML). 10734--10750."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539169"},{"key":"e_1_3_2_2_19_1","unstructured":"Guy Kornowski and Ohad Shamir. 2021. Oracle Complexity in Nonsmooth Nonconvex Optimization. In Advances in Neural Information Processing Systems 34 (NeurIPS). 324--334."},{"key":"e_1_3_2_2_20_1","volume-title":"Proceedings of the 3rd TinyML Research Symposium. 1--8.","author":"Liu Yejia","year":"2023","unstructured":"Yejia Liu, Shijin Duan, Xiaolin Xu, and Shaolei Ren. 2023. MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption. In Proceedings of the 3rd TinyML Research Symposium. 1--8."},{"key":"e_1_3_2_2_21_1","unstructured":"Yong Liu Siqi Mai Minhao Cheng Xiangning Chen Cho-Jui Hsieh and Yang You. 2022. Random Sharpness-Aware Minimization. In Advances in Neural Information Processing Systems 35 (NeurIPS). 24543--24556."},{"key":"e_1_3_2_2_22_1","unstructured":"David Lopez-Paz and Marc'Aurelio Ranzato. 2017. Gradient Episodic Memory for Continual Learning. In Advances in Neural Information Processing Systems 30 (NIPS). 6467--6476."},{"volume-title":"Proceedings of The 28th Conference on Learning Theory (COLT). 1286--1304","author":"Luo Haipeng","key":"e_1_3_2_2_23_1","unstructured":"Haipeng Luo and Robert E. Schapire. 2015. Achieving All with No Parameters: AdaNormalHedge. In Proceedings of The 28th Conference on Learning Theory (COLT). 1286--1304."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00810"},{"key":"e_1_3_2_2_25_1","unstructured":"Behnam Neyshabur Srinadh Bhojanapalli David McAllester and Nati Srebro. 2017. Exploring Generalization in Deep Learning. In Advances in Neural Information Processing Systems 30 (NIPS). 5947--5956."},{"volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. 188--197","author":"Ni Jianmo","key":"e_1_3_2_2_26_1","unstructured":"Jianmo Ni, Jiacheng Li, and Julian J. McAuley. 2019. Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. 188--197."},{"key":"e_1_3_2_2_27_1","unstructured":"Francesco Orabona and D\u00e1vid P\u00e1l. 2016. Coin Betting and Parameter-Free Online Learning. In Advances in Neural Information Processing Systems 29 (NIPS). 577--585."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00162"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/3692070.3693752"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976602753284446"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539262"},{"volume-title":"Machine Learning in Non-stationary Environments: Introduction to Covariate Shift Adaptation","author":"Sugiyama Masashi","key":"e_1_3_2_2_33_1","unstructured":"Masashi Sugiyama and Motoaki Kawanabe. 2012. Machine Learning in Non-stationary Environments: Introduction to Covariate Shift Adaptation. The MIT Press."},{"key":"e_1_3_2_2_34_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML). 9229--9248","author":"Sun Yu","year":"2020","unstructured":"Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei A. Efros, and Moritz Hardt. 2020. Test-time training with self-supervision for generalization under distribution shifts. In Proceedings of the 37th International Conference on Machine Learning (ICML). 9229--9248."},{"key":"e_1_3_2_2_35_1","volume-title":"Well-read students learn better: On the importance of pre-training compact models. ArXiv preprint","author":"Turc Iulia","year":"2019","unstructured":"Iulia Turc, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Well-read students learn better: On the importance of pre-training compact models. ArXiv preprint, Vol. arXiv:1908.08962 (2019)."},{"key":"e_1_3_2_2_36_1","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research, Vol. 9, 11 (2008), 2579--2605.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00706"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599288"},{"key":"e_1_3_2_2_39_1","volume-title":"Online Feature Updates Improve Online (Generalized) Label Shift Adaptation. NeurIPS Workshop on Self-Supervised Learning: Theory and Practice","author":"Wu Ruihan","year":"2023","unstructured":"Ruihan Wu, Siddhartha Datta, Yi Su, Dheeraj Baby, Yu-Xiang Wang, and Kilian Q Weinberger. 2023. Online Feature Updates Improve Online (Generalized) Label Shift Adaptation. NeurIPS Workshop on Self-Supervised Learning: Theory and Practice (2023)."},{"key":"e_1_3_2_2_40_1","volume-title":"Weinberger","author":"Wu Ruihan","year":"2021","unstructured":"Ruihan Wu, Chuan Guo, Yi Su, and Kilian Q. Weinberger. 2021. Online adaptation to label distribution shift. In Advances in Neural Information Processing Systems 34 (NeurIPS). 11340--11351."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00672"},{"key":"e_1_3_2_2_42_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML). 11173--11182","author":"Zhang Jingzhao","year":"2020","unstructured":"Jingzhao Zhang, Hongzhou Lin, Stefanie Jegelka, Suvrit Sra, and Ali Jadbabaie. 2020. Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions. In Proceedings of the 37th International Conference on Machine Learning (ICML). 11173--11182."},{"key":"e_1_3_2_2_43_1","volume-title":"Proceedings of the 30th International Conference on Machine Learning (ICML). 819--827","author":"Zhang Kun","year":"2013","unstructured":"Kun Zhang, Bernhard Sch\u00f6lkopf, Krikamol Muandet, and Zhikun Wang. 2013. Domain Adaptation under Target and Conditional Shift. In Proceedings of the 30th International Conference on Machine Learning (ICML). 819--827."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467389"},{"key":"e_1_3_2_2_45_1","first-page":"1","article-title":"Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization","volume":"25","author":"Zhao Peng","year":"2024","unstructured":"Peng Zhao, Yu-Jie Zhang, Lijun Zhang, and Zhi-Hua Zhou. 2024. Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization. Journal of Machine Learning Research, Vol. 25, 98 (2024), 1--52.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwac123"},{"key":"e_1_3_2_2_47_1","volume-title":"Proceedings of the 20th International Conference on Machine Learning (ICML). 928--936","author":"Zinkevich Martin","year":"2003","unstructured":"Martin Zinkevich. 2003. Online convex programming and generalized infinitesimal gradient ascent. In Proceedings of the 20th International Conference on Machine Learning (ICML). 928--936."}],"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\/3690624.3709182","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:47:50Z","timestamp":1755359270000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709182"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":47,"alternative-id":["10.1145\/3690624.3709182","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709182","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"}}]}}