{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:22:18Z","timestamp":1740169338718,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2021R1A2C2014504 (10%)"],"award-info":[{"award-number":["2021R1A2C2014504 (10%)"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation"},{"DOI":"10.13039\/501100003621","name":"Ministry of Science and ICT","doi-asserted-by":"publisher","award":["2021-0-00106 (40%)","2021-0-00180 (30%)","2021-0-02068 (20%)"],"award-info":[{"award-number":["2021-0-00106 (40%)","2021-0-00180 (30%)","2021-0-02068 (20%)"]}],"id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of New Media and Communications"},{"name":"Brain Korea (BK) 21-Four Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3358275","type":"journal-article","created":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T18:41:21Z","timestamp":1706121681000},"page":"18877-18887","source":"Crossref","is-referenced-by-count":0,"title":["GBMix: Enhancing Fairness by Group-Balanced Mixup"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0270-2781","authenticated-orcid":false,"given":"Sangwoo","family":"Hong","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Communications and Machine Learning Laboratory, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngseok","family":"Yoon","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Communications and Machine Learning Laboratory, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyungjun","family":"Joo","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Communications and Machine Learning Laboratory, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6804-980X","authenticated-orcid":false,"given":"Jungwoo","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Communications and Machine Learning Laboratory, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1120.1641"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.011"},{"key":"ref3","first-page":"19152","article-title":"Fairness without demographics through knowledge distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chai"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-65414-6_9"},{"article-title":"Fair mixup: Fairness via interpolation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chuang","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87240-3_31"},{"article-title":"Model patching: Closing the subgroup performance gap with data augmentation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Goel","key":"ref9"},{"key":"ref10","first-page":"37704","article-title":"UMIX: Improving importance weighting for subpopulation shift via uncertainty-aware mixup","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Han"},{"key":"ref11","article-title":"Equality of opportunity in supervised learning","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Hardt"},{"key":"ref12","first-page":"1929","article-title":"Fairness without demographics in repeated loss minimization","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Hashimoto"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.580"},{"key":"ref14","first-page":"336","article-title":"Simple data balancing achieves competitive worst-group-accuracy","volume-title":"Proc. 1st Conf. Causal Learn. Reasoning","volume":"177","author":"Idrissi"},{"key":"ref15","first-page":"702","article-title":"Identifying and correcting label bias in machine learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Jiang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-011-0463-8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2012.45"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33486-3_3"},{"key":"ref19","first-page":"5275","article-title":"Puzzle mix: Exploiting saliency and local statistics for optimal mixup","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"article-title":"Last layer re-training is sufficient for robustness to spurious correlations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kirichenko","key":"ref20"},{"key":"ref21","first-page":"728","article-title":"Fairness without demographics through adversarially reweighted learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lahoti"},{"key":"ref22","article-title":"Oversampling for imbalanced learning based on K-Means and SMOTE","author":"Last","year":"2017","journal-title":"arXiv:1711.00837"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP49819.2020.9301763"},{"key":"ref24","first-page":"6781","article-title":"Just train twice: Improving group robustness without training group information","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Liu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1432"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_31"},{"key":"ref30","first-page":"14608","article-title":"Using mixup as a regularizer can surprisingly improve accuracy & out-of-distribution robustness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Pinto"},{"key":"ref31","article-title":"On fairness and calibration","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Pleiss","year":"2017"},{"key":"ref32","first-page":"28448","article-title":"Simple and fast group robustness by automatic feature reweighting","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Qiu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctv31xf5v0"},{"key":"ref34","first-page":"8147","article-title":"FR-train: A mutual information-based approach to fair and robust training","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Roh"},{"key":"ref35","first-page":"7584","article-title":"Learning certified individually fair representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ruoss"},{"article-title":"Distributionally robust neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sagawa","key":"ref36"},{"key":"ref37","first-page":"20278","article-title":"GenLabel: Mixup relabeling using generative models","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Sohn"},{"key":"ref38","first-page":"19339","article-title":"No subclass left behind: Fine-grained robustness in coarse-grained classification problems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sohoni"},{"key":"ref39","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"article-title":"The Caltech-UCSD birds-200-2011 dataset","year":"2011","author":"Wah","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00541"},{"key":"ref42","article-title":"Learning to model the tail","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Wang"},{"key":"ref43","first-page":"7139","article-title":"Towards calibrated model for long-tailed visual recognition from prior perspective","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Xu","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411980"},{"key":"ref45","first-page":"25407","article-title":"Improving out-of-distribution robustness via selective augmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yao"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2008.06.108"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"article-title":"Training individually fair ml models with sensitive subspace robustness","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yurochkin","key":"ref48"},{"issue":"75","key":"ref49","first-page":"1","article-title":"Fairness constraints: A flexible approach for fair classification","volume":"20","author":"Zafar","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref50","first-page":"325","article-title":"Learning fair representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zemel"},{"article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang","key":"ref51"},{"key":"ref52","first-page":"26484","article-title":"Correct-n-contrast: A contrastive approach for improving robustness to spurious correlations","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Zhang"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746299"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.463"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10413562.pdf?arnumber=10413562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T09:27:20Z","timestamp":1707816440000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10413562\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3358275","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}