{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:40:03Z","timestamp":1750297203725,"version":"3.41.0"},"reference-count":50,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2025,2,15]],"date-time":"2025-02-15T00:00:00Z","timestamp":1739577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSF of China","doi-asserted-by":"crossref","award":["62336003, 12371510"],"award-info":[{"award-number":["62336003, 12371510"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"NSF for Distinguished Young Scholar of Jiangsu","award":["BK20220080"],"award-info":[{"award-number":["BK20220080"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2025,4,30]]},"abstract":"<jats:p>\n            Feature noise and label noise are ubiquitous in practical scenarios, which pose great challenges for training a robust machine learning model. Most previous approaches usually deal with only a single problem of either feature noise or label noise. However, in real-world applications, hybrid noise, which contains both feature noise and label noise, is very common due to the unreliable data collection and annotation processes. Although some results have been achieved by a few representation learning based attempts, this issue is still far from being addressed with promising performance and guaranteed theoretical analyses. To address the challenge, we propose a novel unified learning framework called\n            <jats:bold>Feature and Label Recovery (FLR)<\/jats:bold>\n            to combat the hybrid noise from the perspective of data recovery, where we concurrently reconstruct both the feature matrix and the label matrix of input data. Specifically, the clean feature matrix is discovered by the low-rank approximation, and the ground-truth label matrix is embedded based on the recovered features with a nuclear norm regularization. Meanwhile, the feature noise and label noise are characterized by their respective adaptive matrix norms to satisfy the corresponding maximum likelihood. As this framework leads to a non-convex optimization problem, we develop the non-convex\n            <jats:bold>Alternating Direction Method of Multipliers (ADMM)<\/jats:bold>\n            with the convergence guarantee to solve our learning objective. We also provide the theoretical analysis to show that the generalization error of FLR can be upper-bounded in the presence of hybrid noise. Experimental results on several typical benchmark datasets clearly demonstrate the superiority of our proposed method over the state-of-the-art robust learning approaches for various noises.\n          <\/jats:p>","DOI":"10.1145\/3709149","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T16:39:46Z","timestamp":1734971986000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust Learning under Hybrid Noise"],"prefix":"10.1145","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9209-6825","authenticated-orcid":false,"given":"Yang","family":"Wei","sequence":"first","affiliation":[{"name":"School of Computer Science, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3848-3397","authenticated-orcid":false,"given":"Shuo","family":"Chen","sequence":"additional","affiliation":[{"name":"RIKEN AIP, Chuo-ku, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6961-7455","authenticated-orcid":false,"given":"Shanshan","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Broadway, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6338-0958","authenticated-orcid":false,"given":"Bo","family":"Han","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1154-6194","authenticated-orcid":false,"given":"Chen","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,2,15]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/1970392.1970395"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2286106"},{"key":"e_1_3_2_4_2","first-page":"11","article-title":"Low-rank latent pattern approximation with applications to robust image classification","volume":"26","author":"Chen Shuo","year":"2017","unstructured":"Shuo Chen, Jian Yang, Lei Luo, Yang Wei, Kaihua Zhang, and Ying Tai. 2017. Low-rank latent pattern approximation with applications to robust image classification. IEEE Transactions on Image Processing 26, 11 (2017), 5519\u20135530.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2901248"},{"key":"e_1_3_2_6_2","first-page":"3447","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Chiang Kaiyang","year":"2015","unstructured":"Kaiyang Chiang, Chojui Hsieh, and Inderjit S. Dhillon. 2015. Matrix completion with noisy side information. In Proceedings of the Advances in Neural Information Processing Systems, 3447\u20133455."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110372"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2007.11-06-397"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10293"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10894"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2941684"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.110"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1973.10489010"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071797"},{"key":"e_1_3_2_15_2","first-page":"5841","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"31","author":"Han Bo","year":"2018","unstructured":"Bo Han, Jiangchao Yao, Gang Niu, Mingyuan Zhou, Ivor Tsang, Ya Zhang, and Masashi Sugiyama. 2018. Masking: A new perspective of noisy supervision. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 31, 5841\u20135851."},{"key":"e_1_3_2_16_2","first-page":"8536","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"31","author":"Han Bo","year":"2018","unstructured":"Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, and Masashi Sugiyama. 2018. Co-teaching: Robust training of deep neural networks with extremely noisy labels. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 31, 8536\u20138546."},{"key":"e_1_3_2_17_2","first-page":"2445","volume-title":"Proceedings of International Conference on Machine Learning","author":"Hsieh Cho-Jui","year":"2015","unstructured":"Cho-Jui Hsieh, Nagarajan Natarajan, and Inderjit Dhillon. 2015. PU learning for matrix completion. In Proceedings of International Conference on Machine Learning, 2445\u20132453."},{"key":"e_1_3_2_18_2","first-page":"2304","volume-title":"Proceedings of International Conference on Machine Learning","author":"Jiang Lu","year":"2018","unstructured":"Lu Jiang, Zhengyuan Zhou, Thomas Leung, Li-Jia Li, and Li Fei-Fei. 2018. MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In Proceedings of International Conference on Machine Learning, 2304\u20132313."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2953337"},{"key":"e_1_3_2_20_2","first-page":"1","volume-title":"Proceedings of International Conference on Learning Representations","author":"Li Junnan","year":"2019","unstructured":"Junnan Li, Richard Socher, and Steven C. H. Hoi. 2019. DivideMix: Learning with noisy labels as semi-supervised learning. In Proceedings of International Conference on Learning Representations, 1\u201314."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00935"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109835"},{"key":"e_1_3_2_23_2","unstructured":"Zhouchen Lin Minming Chen and Yi Ma. 2010. The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices. arXiv:1009.5055. Retrieved from https:\/\/arxiv.org\/abs\/1009.5055"},{"key":"e_1_3_2_24_2","first-page":"663","volume-title":"Proceedings of International Conference on Machine Learning","author":"Liu Guangcan","year":"2010","unstructured":"Guangcan Liu, Zhouchen Lin, and Yong Yu. 2010. Robust subspace segmentation by low-rank representation. In Proceedings of International Conference on Machine Learning, 663\u2013670."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435790"},{"key":"e_1_3_2_26_2","first-page":"2605","volume-title":"Proceedings of International Conference on International Joint Conferences on Artificial Intelligence","author":"Luo Yijing","year":"2021","unstructured":"Yijing Luo, Bo Han, and Chen Gong. 2021. A bi-level formulation for label noise learning with spectral cluster discovery. In Proceedings of International Conference on International Joint Conferences on Artificial Intelligence, 2605\u20132611."},{"key":"e_1_3_2_27_2","first-page":"1","article-title":"Multiscale superpixelwise prophet model for noise-robust feature extraction in hyperspectral images","volume":"61","author":"Ma Ping","year":"2023","unstructured":"Ping Ma, Jinchang Ren, Genyun Sun, Huimin Zhao, Xiuping Jia, Yijun Yan, and Jaime Zabalza. 2023. Multiscale superpixelwise prophet model for noise-robust feature extraction in hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing 61 (2023), 1\u201312.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44673-7_19"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02319-4_50"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.5555\/944249.944255"},{"key":"e_1_3_2_31_2","first-page":"708","volume-title":"Proceedings of International Conference on Machine Learning","author":"Patrini Giorgio","year":"2016","unstructured":"Giorgio Patrini, Frank Nielsen, Richard Nock, and Marcello Carioni. 2016. Loss factorization, weakly supervised learning and label noise robustness. In Proceedings of International Conference on Machine Learning, 708\u2013717."},{"key":"e_1_3_2_32_2","volume-title":"Real Analysis","author":"Royden Halsey","year":"2010","unstructured":"Halsey Royden and Patrick Michael Fitzpatrick. 2010. Real Analysis. China Machine Press."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/2542182.2542197"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108467"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.23919\/CJE.2014.10848028"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626242"},{"key":"e_1_3_2_37_2","first-page":"12","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent Pascal","year":"2010","unstructured":"Pascal Vincent, Hugo Larochelle, Isabelle Lajoie, Yoshua Bengio, Pierre-Antoine Manzagol, and L\u00e9on Bottou. 2010. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research 11, 12 (2010), 3371\u20133408.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2023.00.035"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01374"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2938782"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.79"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939798"},{"key":"e_1_3_2_44_2","first-page":"6225","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"32","author":"Xu Yilun","year":"2019","unstructured":"Yilun Xu, Peng Cao, Yuqing Kong, and Yizhou Wang. 2019. L_dmi: A novel information-theoretic loss function for training deep nets robust to label noise. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 32, 6225\u20136236."},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2535218"},{"key":"e_1_3_2_46_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"36","author":"You Zunzhi","year":"2024","unstructured":"Zunzhi You, Daochang Liu, Bohyung Han, and Chang Xu. 2024. Beyond pretrained features: Noisy image modeling provides adversarial defense. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 36."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3519311"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2811764"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3591363"},{"key":"e_1_3_2_50_2","first-page":"8792","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"31","author":"Zhang Zhilu","year":"2018","unstructured":"Zhilu Zhang and Mert Sabuncu. 2018. Generalized cross entropy loss for training deep neural networks with noisy labels. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 31, 8792\u20138802."},{"key":"e_1_3_2_51_2","first-page":"27633","volume-title":"Proceedings of International Conference on Machine Learning","author":"Zhu Zhaowei","year":"2022","unstructured":"Zhaowei Zhu, Jialu Wang, and Yang Liu. 2022. Beyond images: Label noise transition matrix estimation for tasks with lower-quality features. In Proceedings of International Conference on Machine Learning, 27633\u201327653."}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709149","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3709149","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:31Z","timestamp":1750295851000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709149"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,15]]},"references-count":50,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,4,30]]}},"alternative-id":["10.1145\/3709149"],"URL":"https:\/\/doi.org\/10.1145\/3709149","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"type":"print","value":"2157-6904"},{"type":"electronic","value":"2157-6912"}],"subject":[],"published":{"date-parts":[[2025,2,15]]},"assertion":[{"value":"2024-07-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}