{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T11:40:05Z","timestamp":1750765205496,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,23]]},"DOI":"10.1145\/3715275.3732200","type":"proceedings-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T17:01:18Z","timestamp":1750698078000},"page":"3138-3147","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Fairness of Deep Ensembles: On the interplay between per-group task difficulty and under-representation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4520-7070","authenticated-orcid":false,"given":"Estanislao","family":"Claucich","sequence":"first","affiliation":[{"name":"sinc(i), CONICET & Universidad Nacional del Litoral, Santa Fe, Santa Fe, Argentina"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0190-6459","authenticated-orcid":false,"given":"Sara","family":"Hooker","sequence":"additional","affiliation":[{"name":"Cohere for AI, San Francisco, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2182-4351","authenticated-orcid":false,"given":"Diego H.","family":"Milone","sequence":"additional","affiliation":[{"name":"sinc(i), CONICET & Universidad Nacional del Litoral, Santa Fe, Santa Fe, Argentina"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8500-788X","authenticated-orcid":false,"given":"Enzo","family":"Ferrante","sequence":"additional","affiliation":[{"name":"Institute of Computer Sciences, CONICET & Universidad de Buenos Aires, Buenos Aires, Buenos Aires, Argentina"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6155-8679","authenticated-orcid":false,"given":"Rodrigo","family":"Echeveste","sequence":"additional","affiliation":[{"name":"sinc(i), CONICET & Universidad Nacional del Litoral, Santa Fe, Santa Fe, Argentina"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,23]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01012"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Tom\u00a0L Beauchamp. 2003. Methods and principles in biomedical ethics. Journal of Medical ethics 29 5 (2003) 269\u2013274.","DOI":"10.1136\/jme.29.5.269"},{"key":"e_1_3_3_1_4_2","first-page":"56","volume-title":"MICCAI Workshop on Fairness of AI in Medical Imaging","author":"Belhadj Samia","year":"2024","unstructured":"Samia Belhadj, Sanguk Park, Ambika Seth, Hesham Dar, and Thijs Kooi. 2024. Positive-Sum Fairness: Leveraging Demographic Attributes to Achieve Fair AI Outcomes Without Sacrificing Group Gains. In MICCAI Workshop on Fairness of AI in Medical Imaging. Springer, 56\u201366."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Leo Breiman. 2001. Random Forests. Machine Learning 45 1 (Oct 2001) 5\u201332. https:\/\/doi.org\/10.1023\/A:1010933404324","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_3_1_6_2","first-page":"77","volume-title":"Conference on fairness, accountability and transparency","author":"Buolamwini Joy","year":"2018","unstructured":"Joy Buolamwini and Timnit Gebru. 2018. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Conference on fairness, accountability and transparency. PMLR, 77\u201391."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Simon Caton and Christian Haas. 2024. Fairness in machine learning: A survey. Comput. Surveys 56 7 (2024) 1\u201338.","DOI":"10.1145\/3616865"},{"key":"e_1_3_3_1_8_2","unstructured":"Hugh Chen Scott Lundberg and Su-In Lee. 2017. Checkpoint Ensembles: Ensemble Methods from a Single Training Process. arxiv:https:\/\/arXiv.org\/abs\/1710.03282\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1710.03282"},{"key":"e_1_3_3_1_9_2","unstructured":"Irene Chen Fredrik\u00a0D. Johansson and David Sontag. 2018. Why Is My Classifier Discriminatory? arxiv:https:\/\/arXiv.org\/abs\/1805.12002\u00a0[stat.ML] https:\/\/arxiv.org\/abs\/1805.12002"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45014-9_1"},{"key":"e_1_3_3_1_11_2","unstructured":"Enzo Ferrante and Rodrigo Echeveste. 2024. Open Challenges on Fairness of Artificial Intelligence in Medical Imaging Applications. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.16953 (2024)."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00133"},{"key":"e_1_3_3_1_13_2","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. arxiv:https:\/\/arXiv.org\/abs\/1512.03385\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1512.03385"},{"key":"e_1_3_3_1_14_2","unstructured":"Sara Hooker Nyalleng Moorosi Gregory Clark Samy Bengio and Emily Denton. 2020. Characterising Bias in Compressed Models. arxiv:https:\/\/arXiv.org\/abs\/2010.03058\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2010.03058"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Jeremy Irvin Pranav Rajpurkar Michael Ko Yifan Yu Silviana Ciurea-Ilcus Chris Chute Henrik Marklund Behzad Haghgoo Robyn Ball Katie Shpanskaya Jayne Seekins David\u00a0A. Mong Safwan\u00a0S. Halabi Jesse\u00a0K. Sandberg Ricky Jones David\u00a0B. Larson Curtis\u00a0P. Langlotz Bhavik\u00a0N. Patel Matthew\u00a0P. Lungren and Andrew\u00a0Y. Ng. 2019. CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison. arxiv:https:\/\/arXiv.org\/abs\/1901.07031\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1901.07031","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Patrik Kenfack Adil Khan S.M. Kazmi Rasheed Hussain Alma Oracevic and Asad Khattak. 2021. Impact of Model Ensemble On the Fairness of Classifiers in Machine Learning. 1\u20136. https:\/\/doi.org\/10.1109\/ICAPAI49758.2021.9462068","DOI":"10.1109\/ICAPAI49758.2021.9462068"},{"key":"e_1_3_3_1_17_2","unstructured":"Wei-Yin Ko Daniel D\u2019souza Karina Nguyen Randall Balestriero and Sara Hooker. 2023. Fair-ensemble: When fairness naturally emerges from deep ensembling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.00586 (2023)."},{"key":"e_1_3_3_1_18_2","unstructured":"Balaji Lakshminarayanan Alexander Pritzel and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_56"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Agostina\u00a0J. Larrazabal Nicol\u00e1s Nieto Victoria Peterson Diego\u00a0H. Milone and Enzo Ferrante. 2020. Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis. Proceedings of the National Academy of Sciences of the United States of America 117 23 (Jun 2020) 12592\u201312594. https:\/\/doi.org\/10.1073\/pnas.1919012117 arXiv:PMC7293650","DOI":"10.1073\/pnas.1919012117"},{"key":"e_1_3_3_1_21_2","unstructured":"Stefan Lee Senthil Purushwalkam Michael Cogswell David Crandall and Dhruv Batra. 2015. Why m heads are better than one: Training a diverse ensemble of deep networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1511.06314 (2015)."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/wacv48630.2021.00037"},{"key":"e_1_3_3_1_24_2","unstructured":"Lucas Mansilla Estanislao Claucich Rodrigo Echeveste Diego\u00a0H Milone and Enzo Ferrante. 2024. Demographically-Informed Prediction Discrepancy Index: Early Warnings of Demographic Biases for Unlabeled Populations. Transactions on Machine Learning Research (2024)."},{"key":"e_1_3_3_1_25_2","unstructured":"Giung Nam Jongmin Yoon Yoonho Lee and Juho Lee. 2021. Diversity matters when learning from ensembles. Advances in neural information processing systems 34 (2021) 8367\u20138377."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","unstructured":"Milton Pividori Georgina Stegmayer and Diego\u00a0H. Milone. 2016. Diversity control for improving the analysis of consensus clustering. Information Sciences 361-362 (2016) 120\u2013134. https:\/\/doi.org\/10.1016\/j.ins.2016.04.027","DOI":"10.1016\/j.ins.2016.04.027"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Mar\u00eda\u00a0Agustina Ricci\u00a0Lara Rodrigo Echeveste and Enzo Ferrante. 2022. Addressing fairness in artificial intelligence for medical imaging. nature communications 13 1 (2022) 4581.","DOI":"10.1038\/s41467-022-32186-3"},{"key":"e_1_3_3_1_28_2","unstructured":"Esther Rolf Theodora Worledge Benjamin Recht and Michael\u00a0I. Jordan. 2021. Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data. arxiv:https:\/\/arXiv.org\/abs\/2103.03399\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2103.03399"},{"key":"e_1_3_3_1_29_2","unstructured":"Shiori Sagawa Aditi Raghunathan Pang\u00a0Wei Koh and Percy Liang. 2020. An Investigation of Why Overparameterization Exacerbates Spurious Correlations. arxiv:https:\/\/arXiv.org\/abs\/2005.04345\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2005.04345"},{"key":"e_1_3_3_1_30_2","unstructured":"Kajetan Schweighofer Adrian Arnaiz-Rodriguez Sepp Hochreiter and Nuria Oliver. 2024. The Disparate Benefits of Deep Ensembles. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.13831 (2024)."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Laleh Seyyed-Kalantari Guanxiong Liu Matthew McDermott Irene\u00a0Y. Chen and Marzyeh Ghassemi. 2020. CheXclusion: Fairness gaps in deep chest X-ray classifiers. arxiv:https:\/\/arXiv.org\/abs\/2003.00827\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2003.00827","DOI":"10.1142\/9789811232701_0022"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","unstructured":"Laleh Seyyed-Kalantari Haoran Zhang Matthew B.\u00a0A. McDermott Irene\u00a0Y. Chen and Marzyeh Ghassemi. 2021. Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations. Nature Medicine 27 12 (2021) 2176\u20132182. https:\/\/doi.org\/10.1038\/s41591-021-01595-0","DOI":"10.1038\/s41591-021-01595-0"},{"key":"e_1_3_3_1_33_2","volume-title":"The Eleventh International Conference on Learning Representations","author":"Siddiqui Shoaib\u00a0Ahmed","year":"2023","unstructured":"Shoaib\u00a0Ahmed Siddiqui, Nitarshan Rajkumar, Tegan Maharaj, David Krueger, and Sara Hooker. 2023. Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PvLnIaJbt9"},{"key":"e_1_3_3_1_34_2","unstructured":"Nina Weng Siavash Bigdeli Eike Petersen and Aasa Feragen. 2023. Are Sex-based Physiological Differences the Cause of Gender Bias for Chest X-ray Diagnosis? arxiv:https:\/\/arXiv.org\/abs\/2308.05129\u00a0[eess.IV] https:\/\/arxiv.org\/abs\/2308.05129"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3375709"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Dominik Zietlow Michael Lohaus Guha Balakrishnan Matth\u00e4us Kleindessner Francesco Locatello Bernhard Sch\u00f6lkopf and Chris Russell. 2022. Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers. arxiv:https:\/\/arXiv.org\/abs\/2203.04913\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2203.04913","DOI":"10.1109\/CVPR52688.2022.01016"}],"event":{"name":"FAccT '25: The 2025 ACM Conference on Fairness, Accountability, and Transparency","acronym":"FAccT '25","location":"Athens Greece"},"container-title":["Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3715275.3732200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T11:03:20Z","timestamp":1750763000000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715275.3732200"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,23]]},"references-count":35,"alternative-id":["10.1145\/3715275.3732200","10.1145\/3715275"],"URL":"https:\/\/doi.org\/10.1145\/3715275.3732200","relation":{},"subject":[],"published":{"date-parts":[[2025,6,23]]},"assertion":[{"value":"2025-06-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}