Preserving Fairness in AI under Domain Shift
This addresses the challenge of preserving fairness for AI systems in dynamic real-world environments, representing an incremental improvement over existing methods.
The paper tackles the problem of maintaining fairness in AI models under domain shift, where traditional single-shot training fails due to distributional changes over time, and presents an algorithm that adapts fair models using only new unannotated data, achieving effectiveness validated on three fairness datasets.
Existing algorithms for ensuring fairness in AI use a single-shot training strategy, where an AI model is trained on an annotated training dataset with sensitive attributes and then fielded for utilization. This training strategy is effective in problems with stationary distributions, where both training and testing data are drawn from the same distribution. However, it is vulnerable with respect to distributional shifts in the input space that may occur after the initial training phase. As a result, the time-dependent nature of data can introduce biases into the model predictions. Model retraining from scratch using a new annotated dataset is a naive solution that is expensive and time-consuming. We develop an algorithm to adapt a fair model to remain fair under domain shift using solely new unannotated data points. We recast this learning setting as an unsupervised domain adaptation problem. Our algorithm is based on updating the model such that the internal representation of data remains unbiased despite distributional shifts in the input space. We provide extensive empirical validation on three widely employed fairness datasets to demonstrate the effectiveness of our algorithm.