Li, J., Yao, Y., Pan, Y., Wang, X., Tsang, I. W., & Fu, X. (2025). Alpha and prejudice: Improving α-sized worst-case fairness via intrinsic reweighting. IEEE Transactions on Neural Networks and Learning Systems, 36(10), 18005–18019.
Abstract:
Achieving worst-case group fairness typically relies on maximizing the utility of the worst-off demographic group. However, in practice, demographic information is often unavailable, making direct max-min formulations infeasible. To address this, recent work introduces a relaxed setting, using a lower bound $\alpha$ on the minimal group size—referred to as ``$\alpha$-sized worst-case fairness'' in this paper. We first motivate the importance of this setting by highlighting its relevance to data privacy, a critical yet underexplored perspective.
Rather than simply retraining on worst-off samples, we propose a reweighting approach that assigns sample weights based on their intrinsic contributions to fairness. To handle the global nature of worst-case objectives efficiently, we develop a stochastic learning algorithm that simplifies training without sacrificing performance. We also address the impact of outliers by introducing a robust variant of our method.
Through theoretical analysis and extensive experiments on standard fairness benchmarks, we show that our methods not only connect naturally to existing fairness-through-reweighting approaches but also outperform strong baselines.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation, Singapore and Infocomm Media Development Authority - Trust Tech Funding Initiative
Grant Reference no. : DTC-RGC-04
This research / project is supported by the Singapore Maritime Institute - Maritime AI Research Programme
Grant Reference no. : SMI-2022-MTP-06