Adaptive Fairness-Aware Online Meta-Learning for Changing Environments

TL;DR

This paper introduces a novel adaptive online meta-learning framework, FairSAOML, that ensures fairness in changing environments by balancing accuracy and fairness constraints, outperforming existing methods.

Contribution

It proposes a new regret metric, FairSAR, and an adaptive meta-learning algorithm, FairSAOML, for fairness-aware online learning in non-i.i.d. changing environments.

Findings

FairSAOML achieves sub-linear regret bounds for loss and fairness violations.

Experimental results show significant performance improvements over prior methods.

The framework effectively adapts to dynamic, heterogeneous data distributions.

Abstract

The 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 statistic parity of the new coming task across different protected sub-populations (e.g. race and gender). A major drawback of existing methods is that they make heavy use of the i.i.d assumption for data and hence provide static regret analysis for the framework. However, low static regret cannot imply a good performance in changing environments where tasks are sampled from heterogeneous distributions. To address the fairness-aware online learning problem in changing environments, in this paper, we first construct a novel regret metric FairSAR by adding long-term fairness constraints onto a strongly adapted loss regret. Furthermore, to determine a good model parameter at each round, we propose a novel adaptive fairness-aware online meta-learning algorithm, namely FairSAOML, which is able to adapt to changing environments in both bias control and model precision. The problem is formulated in the form of a bi-level convex-concave optimization with respect to the model's primal and dual parameters that are associated with the model's accuracy and fairness, respectively. The theoretic analysis provides sub-linear upper bounds for both loss regret and violation of cumulative fairness constraints. Our experimental evaluation on different real-world datasets with settings of changing environments suggests that the proposed FairSAOML significantly outperforms alternatives based on the best prior online learning approaches.