{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:10:08Z","timestamp":1750180208808,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,8]],"date-time":"2023-08-08T00:00:00Z","timestamp":1691452800000},"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":[[2023,8,8]]},"DOI":"10.1145\/3600211.3604668","type":"proceedings-article","created":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T18:41:37Z","timestamp":1693334497000},"page":"193-204","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Model Debiasing via Gradient-based Explanation on Representation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8774-0607","authenticated-orcid":false,"given":"Jindi","family":"Zhang","sequence":"first","affiliation":[{"name":"Hong Kong Research Center, Huawei, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1101-2686","authenticated-orcid":false,"given":"Luning","family":"Wang","sequence":"additional","affiliation":[{"name":"Hong Kong Research Center, Huawei, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5746-9545","authenticated-orcid":false,"given":"Dan","family":"Su","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8573-3400","authenticated-orcid":false,"given":"Yongxiang","family":"Huang","sequence":"additional","affiliation":[{"name":"Hong Kong Research Center, Huawei, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8050-2486","authenticated-orcid":false,"given":"Caleb Chen","family":"Cao","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8257-5806","authenticated-orcid":false,"given":"Lei","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}]}],"member":"320","published-online":{"date-parts":[[2023,8,29]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Three naive bayes approaches for discrimination-free classification. Data mining and knowledge discovery 21, 2","author":"Calders Toon","year":"2010","unstructured":"Toon Calders and Sicco Verwer. 2010. Three naive bayes approaches for discrimination-free classification. Data mining and knowledge discovery 21, 2 (2010), 277\u2013292."},{"key":"e_1_3_2_1_2_1","volume-title":"Isolating sources of disentanglement in variational autoencoders. arXiv preprint arXiv:1802.04942","author":"Chen TQ","year":"2018","unstructured":"Ricky\u00a0TQ Chen, Xuechen Li, Roger Grosse, and David Duvenaud. 2018. Isolating sources of disentanglement in variational autoencoders. arXiv preprint arXiv:1802.04942 (2018)."},{"key":"e_1_3_2_1_3_1","unstructured":"Elliot Creager David Madras J\u00f6rn-Henrik Jacobsen Marissa Weis Kevin Swersky Toniann Pitassi and Richard Zemel. 2019. Flexibly fair representation learning by disentanglement. In ICML. PMLR 1436\u20131445."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467251"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372878"},{"key":"e_1_3_2_1_6_1","volume-title":"The accuracy, fairness, and limits of predicting recidivism. Science advances 4, 1","author":"Dressel Julia","year":"2018","unstructured":"Julia Dressel and Hany Farid. 2018. The accuracy, fairness, and limits of predicting recidivism. Science advances 4, 1 (2018), eaao5580."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2090236.2090255"},{"key":"e_1_3_2_1_8_1","volume-title":"Domain-adversarial training of neural networks. The journal of machine learning research 17, 1","author":"Ganin Yaroslav","year":"2016","unstructured":"Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, Fran\u00e7ois Laviolette, Mario Marchand, and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. The journal of machine learning research 17, 1 (2016), 2096\u20132030."},{"key":"e_1_3_2_1_9_1","first-page":"2019","article-title":"South German credit data: Correcting a widely used data set","volume":"4","author":"Groemping U","year":"2019","unstructured":"U Groemping. 2019. South German credit data: Correcting a widely used data set. Rep. Math., Phys. Chem., Berlin, Germany, Tech. Rep 4 (2019), 2019.","journal-title":"Rep. Math., Phys. Chem., Berlin, Germany, Tech. Rep"},{"key":"e_1_3_2_1_10_1","volume-title":"Equality of opportunity in supervised learning. Advances in neural information processing systems 29","author":"Hardt Moritz","year":"2016","unstructured":"Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of opportunity in supervised learning. Advances in neural information processing systems 29 (2016), 3315\u20133323."},{"key":"e_1_3_2_1_11_1","unstructured":"Irina Higgins Loic Matthey Arka Pal Christopher Burgess Xavier Glorot Matthew Botvinick Shakir Mohamed and Alexander Lerchner. 2017. beta-vae: Learning basic visual concepts with a constrained variational framework. In ICLR."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00922"},{"key":"e_1_3_2_1_13_1","unstructured":"Hyunjik Kim and Andriy Mnih. 2018. Disentangling by factorising. In ICML. PMLR 2649\u20132658."},{"key":"e_1_3_2_1_14_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma P","year":"2013","unstructured":"Diederik\u00a0P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"volume-title":"ifair: Learning individually fair data representations for algorithmic decision making. In 2019 ieee 35th ICDE)","author":"Lahoti Preethi","key":"e_1_3_2_1_15_1","unstructured":"Preethi Lahoti, Krishna\u00a0P Gummadi, and Gerhard Weikum. 2019. ifair: Learning individually fair data representations for algorithmic decision making. In 2019 ieee 35th ICDE). IEEE, 1334\u20131345."},{"key":"e_1_3_2_1_16_1","volume-title":"Operationalizing individual fairness with pairwise fair representations. arXiv preprint arXiv:1907.01439","author":"Lahoti Preethi","year":"2019","unstructured":"Preethi Lahoti, Krishna\u00a0P Gummadi, and Gerhard Weikum. 2019. Operationalizing individual fairness with pairwise fair representations. arXiv preprint arXiv:1907.01439 (2019)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098077"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_3_2_1_19_1","volume-title":"On the fairness of disentangled representations. arXiv preprint arXiv:1905.13662","author":"Locatello Francesco","year":"2019","unstructured":"Francesco Locatello, Gabriele Abbati, Tom Rainforth, Stefan Bauer, Bernhard Sch\u00f6lkopf, and Olivier Bachem. 2019. On the fairness of disentangled representations. arXiv preprint arXiv:1905.13662 (2019)."},{"key":"e_1_3_2_1_20_1","unstructured":"Francesco Locatello Stefan Bauer Mario Lucic Gunnar Raetsch Sylvain Gelly Bernhard Sch\u00f6lkopf and Olivier Bachem. 2019. Challenging common assumptions in the unsupervised learning of disentangled representations. In ICML. PMLR 4114\u20134124."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372867"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482425"},{"volume-title":"Deep generative models: Survey. In 2018 ISCV","author":"Oussidi Achraf","key":"e_1_3_2_1_23_1","unstructured":"Achraf Oussidi and Azeddine Elhassouny. 2018. Deep generative models: Survey. In 2018 ISCV. IEEE, 1\u20138."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16341"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314278"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_27_1","volume-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034","author":"Simonyan Karen","year":"2013","unstructured":"Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. 2013. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)."},{"key":"e_1_3_2_1_28_1","volume-title":"Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825","author":"Smilkov Daniel","year":"2017","unstructured":"Daniel Smilkov, Nikhil Thorat, Been Kim, Fernanda Vi\u00e9gas, and Martin Wattenberg. 2017. Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825 (2017)."},{"key":"e_1_3_2_1_29_1","volume-title":"Algorithmic bias: should students pay the price?Ai & Society 35, 4","author":"Smith Helen","year":"2020","unstructured":"Helen Smith. 2020. Algorithmic bias: should students pay the price?Ai & Society 35, 4 (2020), 1077\u20131078."},{"key":"e_1_3_2_1_30_1","volume-title":"Full-gradient representation for neural network visualization. arXiv preprint arXiv:1905.00780","author":"Srinivas Suraj","year":"2019","unstructured":"Suraj Srinivas and Fran\u00e7ois Fleuret. 2019. Full-gradient representation for neural network visualization. arXiv preprint arXiv:1905.00780 (2019)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372837"},{"volume-title":"Fairness definitions explained. In 2018 ieee\/acm international workshop on software fairness (fairware)","author":"Verma Sahil","key":"e_1_3_2_1_32_1","unstructured":"Sahil Verma and Julia Rubin. 2018. Fairness definitions explained. In 2018 ieee\/acm international workshop on software fairness (fairware). IEEE, 1\u20137."},{"key":"e_1_3_2_1_33_1","volume-title":"Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning. arXiv preprint arXiv:2106.02705","author":"Wang Yuyan","year":"2021","unstructured":"Yuyan Wang, Xuezhi Wang, Alex Beutel, Flavien Prost, Jilin Chen, and Ed\u00a0H Chi. 2021. Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning. arXiv preprint arXiv:2106.02705 (2021)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452777"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278779"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452787"}],"event":{"name":"AIES '23: AAAI\/ACM Conference on AI, Ethics, and Society","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence"],"location":"Montr\u00e9al QC Canada","acronym":"AIES '23"},"container-title":["Proceedings of the 2023 AAAI\/ACM Conference on AI, Ethics, and Society"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3600211.3604668","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3600211.3604668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:39Z","timestamp":1750178259000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3600211.3604668"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,8]]},"references-count":36,"alternative-id":["10.1145\/3600211.3604668","10.1145\/3600211"],"URL":"https:\/\/doi.org\/10.1145\/3600211.3604668","relation":{},"subject":[],"published":{"date-parts":[[2023,8,8]]},"assertion":[{"value":"2023-08-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}