{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:42:30Z","timestamp":1760244150800,"version":"3.41.0"},"reference-count":30,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2024,4,29]],"date-time":"2024-04-29T00:00:00Z","timestamp":1714348800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Start-up fund of Baylor University, by the National Science Foundation","award":["2147375 and 1750911"],"award-info":[{"award-number":["2147375 and 1750911"]}]},{"name":"National Center for Transportation Cybersecurity and Resiliency (TraCR) headquartered in Clemson, South Carolina, USA"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2024,7,31]]},"abstract":"<jats:p>The fairness-aware online learning framework has emerged as a potent tool within the context of continuous lifelong learning. In this scenario, the learner\u2019s objective is to progressively acquire new tasks as they arrive over time, while also guaranteeing statistical parity among various protected sub-populations, such as race and gender when it comes to the newly introduced tasks. A significant limitation of current approaches lies in their heavy reliance on the i.i.d (independent and identically distributed) assumption concerning data, leading to a static regret analysis of the framework. Nevertheless, it\u2019s crucial to note that achieving low static regret does not necessarily translate to strong performance in dynamic environments characterized by tasks sampled from diverse distributions. In this article, to tackle the fairness-aware online learning challenge in evolving settings, we introduce a unique regret measure, FairSAR, by incorporating long-term fairness constraints into a strongly adapted loss regret framework. Moreover, to determine an optimal model parameter at each time step, we introduce an innovative adaptive fairness-aware online meta-learning algorithm, referred to as FairSAOML. This algorithm possesses the ability to adjust to dynamic environments by effectively managing bias control and model accuracy. The problem is framed as a bi-level convex-concave optimization, considering both the model\u2019s primal and dual parameters, which pertain to its accuracy and fairness attributes, respectively. Theoretical analysis yields sub-linear upper bounds for both loss regret and the cumulative violation of fairness constraints. Our experimental evaluation of various real-world datasets in dynamic environments demonstrates that our proposed FairSAOML algorithm consistently outperforms alternative approaches rooted in the most advanced prior online learning methods.<\/jats:p>","DOI":"10.1145\/3648684","type":"journal-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T12:26:57Z","timestamp":1708432017000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Dynamic Environment Responsive Online Meta-Learning with Fairness Awareness"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6400-0048","authenticated-orcid":false,"given":"Chen","family":"Zhao","sequence":"first","affiliation":[{"name":"Baylor University, Waco, Texas, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9648-2301","authenticated-orcid":false,"given":"Feng","family":"Mi","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas, Richardson, Texas, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2823-3063","authenticated-orcid":false,"given":"Xintao","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Arkansas, Fayetteville, Arkansas, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8053-3443","authenticated-orcid":false,"given":"Kai","family":"Jiang","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas, Richardson, Texas, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9300-1576","authenticated-orcid":false,"given":"Latifur","family":"Khan","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas, Richardson, Texas, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4508-5963","authenticated-orcid":false,"given":"Feng","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas, Richardson, Texas, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,4,29]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","unstructured":"Dan Biddle. 2006. Adverse impact and test validation: A practitioner\u2019s guide to valid and defensible employment testing. Gower page 220. DOI:10.4324\/9781315263298","DOI":"10.4324\/9781315263298"},{"key":"e_1_3_2_3_2","article-title":"Prediction, Learning, and Games","author":"Cesa-Bianchi Nicol\u00f2","year":"2006","unstructured":"Nicol\u00f2 Cesa-Bianchi and G\u00e1bor Lugosi. 2006. Prediction, Learning, and Games. Cambridge University Press","journal-title":"Cambridge University Press"},{"key":"e_1_3_2_4_2","volume-title":"Proceedings of the ICML","author":"Daniely Amit","year":"2015","unstructured":"Amit Daniely, Alon Gonen, and Shai Shalev-Shwartz. 2015. Strongly adaptive online learning. In Proceedings of the ICML."},{"key":"e_1_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Cynthia Dwork et\u00a0al. 2012. Fairness through awareness. In Proceedings of the 3rd Innovations in Theoretical Computer Science Conference.","DOI":"10.1145\/2090236.2090255"},{"key":"e_1_3_2_6_2","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of the ICML.","journal-title":"In Proceedings of the ICML."},{"key":"e_1_3_2_7_2","article-title":"Online meta-learning.","author":"Finn Chelsea","year":"2019","unstructured":"Chelsea Finn, Aravind Rajeswaran, Sham Kakade, and Sergey Levine. 2019. Online meta-learning. In Proceedings of the ICML.","journal-title":"In Proceedings of the ICML."},{"key":"e_1_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Andr\u00e1s Gyorgy Tam\u00e1s Linder and G\u00e1bor Lugosi. 2012. Efficient tracking of large classes of experts. IEEE Transactions on Information Theory 58 11 (2012) 6709\u20136725.","DOI":"10.1109\/TIT.2012.2209627"},{"key":"e_1_3_2_9_2","unstructured":"Moritz Hardt Eric Price and Nati Srebro. 2016. Equality of opportunity in supervised learning. Advances in Neural Information Processing Systems. 3323\u20133331."},{"key":"e_1_3_2_10_2","volume-title":"Proceedings of the 33rd Conference on Learning Theory","author":"Hazan Elad","year":"2020","unstructured":"Elad Hazan and Edgar Minasyan. 2020. Faster projection-free online learning. In Proceedings of the 33rd Conference on Learning Theory."},{"key":"e_1_3_2_11_2","unstructured":"Elad Hazan and Comandur Seshadhri. 2007. Adaptive algorithms for online decision problems. Electronic Colloquium on Computational Complexity (ECCC). 14 088 (2007)."},{"key":"e_1_3_2_12_2","article-title":"Adaptive algorithms for online convex optimization with long-term constraints","author":"Jenatton Rodolphe","year":"2016","unstructured":"Rodolphe Jenatton, Jim Huang, and Cedric Archambeau. 2016. Adaptive algorithms for online convex optimization with long-term constraints. Proceedings of the ICML.","journal-title":"Proceedings of the ICML."},{"key":"e_1_3_2_13_2","volume-title":"Proceedings of the AISTATS","author":"Jun Kwang-Sung","year":"2017","unstructured":"Kwang-Sung Jun, Francesco Orabona, Stephen Wright, and Rebecca Willett. 2017. Improved strongly adaptive online learning using coin betting. In Proceedings of the AISTATS."},{"key":"e_1_3_2_14_2","volume-title":"Proceedings of the ICML","author":"Koh Pang Wei","year":"2021","unstructured":"Pang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Irena Gao, Tony Lee, Etienne David, Ian Stavness, Wei Guo, Berton Earnshaw, Imran Haque, Sara M. Beery, Jure Leskovec, Anshul Kundaje, Emma Pierson, Sergey Levine, Chelsea Finn, and Percy Liang. 2021. WILDS: A benchmark of in-the-wild distribution shifts. In Proceedings of the ICML."},{"key":"e_1_3_2_15_2","volume-title":"Proceedings of the ICML","author":"Lohaus Michael","year":"2020","unstructured":"Michael Lohaus, Michael Perrot, and Ulrike Von Luxburg. 2020. Too relaxed to be fair. In Proceedings of the ICML."},{"key":"e_1_3_2_16_2","first-page":"1286","volume-title":"Proceedings of the Conference on Learning Theory","author":"Luo Haipeng","year":"2015","unstructured":"Haipeng Luo and Robert E. Schapire. 2015. Achieving all with no parameters: Adanormalhedge. In Proceedings of the Conference on Learning Theory. PMLR, 1286\u20131304."},{"key":"e_1_3_2_17_2","unstructured":"Mehrdad Mahdavi Rong Jin and Tianbao Yang. 2012. Trading regret for efficiency: online convex optimization with long term constraints. The Journal of Machine Learning Research 13.1 (2012) 2503\u20132528."},{"key":"e_1_3_2_18_2","article-title":"Is an algorithm less racist than a loan officer?","author":"Miller Jennifer","year":"2020","unstructured":"Jennifer Miller. 2020. Is an algorithm less racist than a loan officer? Retrieved Sept. 18 2020 fromhttps:\/\/www.nytimes.com\/2020\/09\/18\/business\/digital-mortgages.html","journal-title":"Retrieved Sept. 18 2020 from"},{"key":"e_1_3_2_19_2","unstructured":"Yuanyu Wan Bo Xue and Lijun Zhang. 2021. Projection-free online learning in dynamic environments. InProceedings of the AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449820"},{"key":"e_1_3_2_21_2","article-title":"On convexity and bounds of fairness-aware classification","author":"Wu Yongkai","year":"2019","unstructured":"Yongkai Wu, Lu Zhang, and Xintao Wu. 2019. On convexity and bounds of fairness-aware classification. In Proceedings of the WWW.","journal-title":"Proceedings of the WWW"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6116"},{"key":"e_1_3_2_23_2","unstructured":"Jianjun Yuan and Andrew Lamperski. 2018. Online convex optimization for cumulative constraints. Advances in Neural Information Processing Systems. 6140\u20136149."},{"key":"e_1_3_2_24_2","unstructured":"Lijun Zhang Shiyin Lu and Tianbao Yang. 2020. Minimizing dynamic regret and adaptive regret simultaneously. In Proceedings of the International Conference on Artificial Intelligence and Statistics."},{"key":"e_1_3_2_25_2","unstructured":"Lijun Zhang Shiyin Lu and Zhi-Hua Zhou. 2018. Adaptive online learning in dynamic environments. Advances in Neural Information Processing Systems. 1323\u20131333."},{"key":"e_1_3_2_26_2","volume-title":"Fairness-Aware Multi-Task and Meta Learning","author":"Zhao Chen","year":"2021","unstructured":"Chen Zhao. 2021. Fairness-Aware Multi-Task and Meta Learning. Ph. D. Dissertation."},{"key":"e_1_3_2_27_2","article-title":"Rank-based multi-task learning for fair regression","author":"Zhao Chen","year":"2019","unstructured":"Chen Zhao and Feng Chen. 2019. Rank-based multi-task learning for fair regression. In Proceedings of the IEEE International Conference on Data Mining (ICDM).","journal-title":"In Proceedings of the IEEE International Conference on Data Mining (ICDM)."},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Chen Zhao and Feng Chen. 2020. Unfairness discovery and prevention for few-shot regression. In Proceedings of the 2020 IEEE International Conference on Knowledge Graph (ICKG).","DOI":"10.1109\/ICBK50248.2020.00029"},{"key":"e_1_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Chen Zhao Feng Chen and Bhavani Thuraisingham. 2021. Fairness-aware online meta-learning. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.","DOI":"10.1145\/3447548.3467389"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539420"},{"key":"e_1_3_2_31_2","article-title":"Online convex programming and generalized infinitesimal gradient ascent","author":"Zinkevich Martin","year":"2003","unstructured":"Martin Zinkevich. 2003. Online convex programming and generalized infinitesimal gradient ascent. In Proceedings of the ICML.","journal-title":"In Proceedings of the ICML."}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3648684","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3648684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:20Z","timestamp":1750287020000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3648684"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,29]]},"references-count":30,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,7,31]]}},"alternative-id":["10.1145\/3648684"],"URL":"https:\/\/doi.org\/10.1145\/3648684","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"type":"print","value":"1556-4681"},{"type":"electronic","value":"1556-472X"}],"subject":[],"published":{"date-parts":[[2024,4,29]]},"assertion":[{"value":"2023-09-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}