{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:45:32Z","timestamp":1782758732274,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Lundbeck foundation","award":["R436-2023-857"],"award-info":[{"award-number":["R436-2023-857"]}]},{"name":"TRUSTMIND","award":["R453-2024-356"],"award-info":[{"award-number":["R453-2024-356"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,25]]},"DOI":"10.1145\/3805689.3806732","type":"proceedings-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T16:20:39Z","timestamp":1782231639000},"page":"81-105","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Diagnosing Algorithmic Bias: A Group Influence Framework for Fairness Auditing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5458-9795","authenticated-orcid":false,"given":"Olalekan Joseph","family":"Akintande","sequence":"first","affiliation":[{"name":"DTU Compute, Danmarks Tekniske Universitet, Lyngby, Copenhagen, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1274-2888","authenticated-orcid":false,"given":"Amirreza","family":"Takhsha","sequence":"additional","affiliation":[{"name":"Islamic Azad University, Saveh, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3812-7942","authenticated-orcid":false,"given":"Sune H","family":"Holm","sequence":"additional","affiliation":[{"name":"K\u00f8benhavns Universitet, Copenhagen, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9945-981X","authenticated-orcid":false,"given":"Aasa","family":"Feragen","sequence":"additional","affiliation":[{"name":"DTU Compute, Danmarks Tekniske Universitet, Lyngby, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2569-6473","authenticated-orcid":false,"given":"Siavash","family":"Bigdeli","sequence":"additional","affiliation":[{"name":"DTU Compute, Danmarks Tekniske Universitet, Lyngby, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the Fourth European Workshop on Algorithmic Fairness (EWAF 2025). Proceedings of Machine Learning Research (PMLR)","volume":"294","author":"Akintande Olalekan Joseph","year":"2025","unstructured":"Olalekan Joseph Akintande, Siavash Bigdeli, and Aasa Feragen. 2025. Medicine after death: XAI and algorithmic fairness under label bias. In Proceedings of the Fourth European Workshop on Algorithmic Fairness (EWAF 2025). Proceedings of Machine Learning Research (PMLR), Vol. 294, 171\u2013186."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2024.200350"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604723"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-73200-4_50"},{"key":"e_1_3_2_1_5_1","volume-title":"ProPublica Investigative Report","author":"Angwin Julia","year":"2016","unstructured":"Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. 2016. Machine bias: There's software used across the country to predict future criminals. And it's biased against blacks. ProPublica Investigative Report, May 23, 2016. URL: https:\/\/www.propublica.org\/article\/machine-bias-risk-assessments-in-criminal-sentencing."},{"key":"e_1_3_2_1_6_1","volume-title":"Fairness and Machine Learning: Limitations and Opportunities","author":"Barocas Solon","unstructured":"Solon Barocas, Moritz Hardt, and Arvind Narayanan. 2019. Fairness and Machine Learning: Limitations and Opportunities. MIT Press (forthcoming). Online version: https:\/\/fairmlbook.org."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML","volume":"97","author":"Brunet Marc-Etienne","year":"2019","unstructured":"Marc-Etienne Brunet, Colleen Alkalay-Houlihan, Ashton Anderson, and Richard Zemel. 2019. Understanding the origins of bias in word embeddings. In Proceedings of the 36th International Conference on Machine Learning (ICML 2019). PMLR, Vol. 97, 803\u2013811."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 1st Conference on Fairness, Accountability and Transparency (FAccT","volume":"81","author":"Buolamwini Joy","year":"2018","unstructured":"Joy Buolamwini and Timnit Gebru. 2018. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Proceedings of the 1st Conference on Fairness, Accountability and Transparency (FAccT 2018). PMLR, Vol. 81, 77\u201391."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1977.10489493"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1986.tb01392.x"},{"key":"e_1_3_2_1_11_1","first-page":"1","article-title":"Optimization with non-differentiable constraints with applications to fairness, recall, churn, and other goals","volume":"20","author":"Cotter Andrew","year":"2019","unstructured":"Andrew Cotter, Heinrich Jiang, Serena Wang, Taman Narayan, Maya Gupta, Seungil You, and Karthik Sridharan. 2019. Optimization with non-differentiable constraints with applications to fairness, recall, churn, and other goals. Journal of Machine Learning Research 20 (2019), 1\u201359. arXiv:1809.04198.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_12_1","volume-title":"Frederik Zuiderveen Borgesius, and Asia J. Biega","author":"Fabris Alessandro","year":"2025","unstructured":"Alessandro Fabris, Nina Baranowska, Matthew J. Dennis, David Graus, Philipp Hacker, Jorge Saldivar, Frederik Zuiderveen Borgesius, and Asia J. Biega. 2025. Fairness and bias in algorithmic hiring: A multidisciplinary survey. arXiv:2309.13933v4 [cs.CY]."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Emilio Ferrara. 2023. Fairness and bias in artificial intelligence: A brief survey of sources impacts and mitigation strategies. arXiv:2304.07683v2 [cs.CY].","DOI":"10.2196\/preprints.48399"},{"key":"e_1_3_2_1_14_1","volume-title":"Meel","author":"Ghosh Bishwamittra","year":"2023","unstructured":"Bishwamittra Ghosh, Debabrota Basu, and Kuldeep S. Meel. 2023. \u201cHow biased are your features?\u201d: Computing fairness influence functions with global sensitivity analysis. arXiv:2206.00667v3 [cs.LG]."},{"key":"e_1_3_2_1_15_1","volume-title":"Stahel","author":"Hampel Frank R.","year":"1986","unstructured":"Frank R. Hampel, Elvezio M. Ronchetti, Peter J. Rousseeuw, and Werner A. Stahel. 1986. Robust Statistics: The Approach Based on Influence Functions. John Wiley & Sons, New York, NY."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3631326"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-011-0463-8"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML","volume":"80","author":"Kearns Michael","year":"2018","unstructured":"Michael Kearns, Seth Neel, Aaron Roth, and Zhiwei Steven Wu. 2018. Preventing fairness gerrymandering: Auditing and learning for subgroup fairness. In Proceedings of the 35th International Conference on Machine Learning (ICML 2018). PMLR, Vol. 80, 2564\u20132572."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS","volume":"89","author":"Khanna Rajiv","year":"2019","unstructured":"Rajiv Khanna, Been Kim, Joydeep Ghosh, and Oluwasanmi Koyejo. 2019. Interpreting black box predictions using Fisher kernels. In Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019). PMLR, Vol. 89, 3382\u20133390."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.4230\/LIPIcs.ITCS.2017.43"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML 2017","volume":"70","author":"Koh Pang Wei","year":"2017","unstructured":"Pang Wei Koh and Percy Liang. 2017. Understanding black-box predictions via influence functions. In Proceedings of the 34th International Conference on Machine Learning (ICML 2017). PMLR, Vol. 70, 1885\u20131894. arXiv:1703.04730."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00119"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 26th International Conference on Artificial Intelligence and Statistics (AISTATS","volume":"216","author":"Leemann Tobias","year":"2023","unstructured":"Tobias Leemann, Michael Kirchhof, Yao Rong, Enkelejda Kasneci, and Gjergji Kasneci. 2023. When are post-hoc conceptual explanations identifiable? In Proceedings of the 26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023). PMLR, Vol. 216. URL: https:\/\/proceedings.mlr.press\/v216\/leemann23a\/leemann23a.pdf."},{"key":"e_1_3_2_1_24_1","volume-title":"Lundberg and Su-In Lee","author":"Scott","year":"2017","unstructured":"Scott M. Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems 30 (NeurIPS 2017). Curran Associates, Inc., 4765\u20134774. arXiv:1705.07874."},{"key":"e_1_3_2_1_25_1","unstructured":"Julio Mattos Daniel H. Lina and Andr\u00e9 Silva. 2025. Breaking the dyadic barrier: Rethinking fairness in link prediction beyond demographic parity. arXiv:2511.06568v2 [cs.LG]."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3457607"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92648-8"},{"key":"e_1_3_2_1_28_1","volume-title":"Inc.","author":"Pruthi Garvit","year":"2020","unstructured":"Garvit Pruthi, Frederick Liu, Satyen Kale, and Mukund Sundararajan. 2020. Estimating training data influence by tracing gradient descent. In Advances in Neural Information Processing Systems 33 (NeurIPS 2020). Curran Associates, Inc., 19920\u201319930."},{"key":"e_1_3_2_1_29_1","unstructured":"ProPublica. 2016. How we analyzed the COMPAS recidivism algorithm. URL: https:\/\/www.propublica.org\/article\/how-we-analyzed-the-compas-recidivism-algorithm."},{"key":"e_1_3_2_1_30_1","unstructured":"Andrea Schioppa Polina Zablotskaia David Vilar and Artem Sokolov. 2021. Scaling up influence functions. arXiv:2112.03052v1 [cs.LG]."},{"key":"e_1_3_2_1_31_1","volume-title":"Wisconsin Supreme Court, decided","author":"v. Loomis State","year":"2016","unstructured":"State v. Loomis. 2016. 2016 WI 68, 371 Wis. 2d 235, 881 N.W.2d 749. Wisconsin Supreme Court, decided July 13, 2016."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1177\/17456916221134490"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML","volume":"139","author":"Wang Zeyu","year":"2021","unstructured":"Zeyu Wang and Olga Russakovsky. 2021. Directional bias amplification. In Proceedings of the 38th International Conference on Machine Learning (ICML 2021). PMLR, Vol. 139, 10882\u201310893. arXiv:2102.12594."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Haobo Wang Zhaodi Wu and Wei He. 2024a. FairIF: Boosting fairness in deep learning via influence functions with validation set sensitive attributes. arXiv:2201.05759v2 [cs.LG].","DOI":"10.1145\/3616855.3635844"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Yifan Wang Peijie Sun Weizhi Ma Min Zhang Yu Zhang Peng Jiang and Shaoping Ma. 2024b. Intersectional two-sided fairness in recommendation. arXiv:2402.02816v2 [cs.IR].","DOI":"10.1145\/3589334.3645518"},{"key":"e_1_3_2_1_36_1","volume-title":"Arik","author":"Yeh Chih-Kuan","year":"2018","unstructured":"Chih-Kuan Yeh, Been Kim, Pradeep Ravikumar, and Sercan O. Arik. 2018. Representer point selection for explaining deep neural networks. In Advances in Neural Information Processing Systems 31 (NeurIPS 2018). Curran Associates, Inc., 9291\u20139301. arXiv:1811.09720."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278779"}],"event":{"name":"FAccT '26: The 2026 ACM Conference on Fairness, Accountability, and Transparency","location":"Montreal QC Canada","acronym":"FAccT '26","sponsor":["ACM\/SIG"]},"container-title":["Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805689.3806732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:12:22Z","timestamp":1782756742000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805689.3806732"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":37,"alternative-id":["10.1145\/3805689.3806732","10.1145\/3805689"],"URL":"https:\/\/doi.org\/10.1145\/3805689.3806732","relation":{},"subject":[],"published":{"date-parts":[[2026,6,25]]},"assertion":[{"value":"2026-06-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}