Abstract
The fairness-aware online learning framework has emerged as a potent tool within the context of continuous lifelong learning. In this scenario, the learner’s 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’s 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’s 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.
- [1] Dan Biddle. 2006. Adverse impact and test validation: A practitioner’s guide to valid and defensible employment testing. Gower, page 220.
DOI: Google ScholarCross Ref - [2] . 2006. Prediction, Learning, and Games. Cambridge University PressGoogle Scholar
- [3] . 2015. Strongly adaptive online learning. In Proceedings of the ICML.Google Scholar
- [4] Cynthia Dwork, et al. 2012. Fairness through awareness. In Proceedings of the 3rd Innovations in Theoretical Computer Science Conference.Google Scholar
- [5] . 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of the ICML.Google Scholar
- [6] . 2019. Online meta-learning. In Proceedings of the ICML.Google Scholar
- [7] András Gyorgy, Tamás Linder, and Gábor Lugosi. 2012. Efficient tracking of large classes of experts. IEEE Transactions on Information Theory 58, 11 (2012), 6709–6725.Google Scholar
- [8] Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of opportunity in supervised learning. Advances in Neural Information Processing Systems. 3323–3331.Google Scholar
- [9] . 2020. Faster projection-free online learning. In Proceedings of the 33rd Conference on Learning Theory.Google Scholar
- [10] Elad Hazan, and Comandur Seshadhri. 2007. Adaptive algorithms for online decision problems. Electronic Colloquium on Computational Complexity (ECCC). 14, 088 (2007).Google Scholar
- [11] . 2016. Adaptive algorithms for online convex optimization with long-term constraints. Proceedings of the ICML.Google Scholar
- [12] . 2017. Improved strongly adaptive online learning using coin betting. In Proceedings of the AISTATS.Google Scholar
- [13] . 2021. WILDS: A benchmark of in-the-wild distribution shifts. In Proceedings of the ICML.Google Scholar
- [14] . 2020. Too relaxed to be fair. In Proceedings of the ICML.Google Scholar
- [15] . 2015. Achieving all with no parameters: Adanormalhedge. In Proceedings of the Conference on Learning Theory. PMLR, 1286–1304.Google Scholar
- [16] 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), 2503–2528.Google Scholar
- [17] . 2020. Is an algorithm less racist than a loan officer? Retrieved Sept. 18 2020 from https://www.nytimes.com/2020/09/18/business/digital-mortgages.htmlGoogle Scholar
- [18] . 2021. Projection-free online learning in dynamic environments. InProceedings of the AAAI Conference on Artificial Intelligence.Google Scholar
- [19] . 2021. CLEAR: Contrastive-prototype learning with drift estimation for resource constrained stream mining. In Proceedings of the WWW.Google ScholarDigital Library
- [20] . 2019. On convexity and bounds of fairness-aware classification. In Proceedings of the WWW.Google Scholar
- [21] . 2020. Efficient projection-free online methods with stochastic recursive gradient. In Proceedings of the AAAI.Google ScholarCross Ref
- [22] Jianjun Yuan and Andrew Lamperski. 2018. Online convex optimization for cumulative constraints. Advances in Neural Information Processing Systems. 6140–6149.Google Scholar
- [23] . 2020. Minimizing dynamic regret and adaptive regret simultaneously. In Proceedings of the International Conference on Artificial Intelligence and Statistics.Google Scholar
- [24] Lijun Zhang, Shiyin Lu, and Zhi-Hua Zhou. 2018. Adaptive online learning in dynamic environments. Advances in Neural Information Processing Systems. 1323–1333.Google Scholar
- [25] . 2021. Fairness-Aware Multi-Task and Meta Learning. Ph. D. Dissertation.Google Scholar
- [26] . 2019. Rank-based multi-task learning for fair regression. In Proceedings of the IEEE International Conference on Data Mining (ICDM).Google Scholar
- [27] . 2020. Unfairness discovery and prevention for few-shot regression. In Proceedings of the 2020 IEEE International Conference on Knowledge Graph (ICKG).Google Scholar
- [28] . 2021. Fairness-aware online meta-learning. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.Google Scholar
- [29] . 2022. Adaptive fairness-aware online meta-learning for changing environments. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2565–2575.Google ScholarDigital Library
- [30] . 2003. Online convex programming and generalized infinitesimal gradient ascent. In Proceedings of the ICML.Google Scholar
Index Terms
- Dynamic Environment Responsive Online Meta-Learning with Fairness Awareness
Recommendations
Adaptive Fairness-Aware Online Meta-Learning for Changing Environments
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningThe fairness-aware online learning framework has arisen as a powerful tool for the continual lifelong learning setting. The goal for the learner is to sequentially learn new tasks where they come one after another over time and the learner ensures the ...
Airtime Fairness for IEEE 802.11 Multirate Networks
Under a multi rate network scenario, the IEEE 802.11 DCF MAC fails to provide air-time fairness for all competing stations since the protocol is designed for ensuring max-min throughput fairness and the maximum achievable throughput by any station gets ...
Dynamic Contention Window Control Mechanism to Achieve Fairness between Uplink and Downlink Flows in IEEE 802.11 Wireless LANs
This paper considers a fairness issue between uplink and downlink flows in IEEE 802.11 wireless LANs, where uplink flows dominate over downlink flows in terms of wireless bandwidth usage. As a solution to this unfairness, we propose modifying the IEEE ...
Comments