Towards Harmless Rawlsian Fairness Regardless of Demographic Prior
This work addresses the challenge of ensuring fairness in AI systems when demographic data is unavailable, which is crucial for privacy-sensitive applications, though it is incremental as it builds on existing fairness methods.
The paper tackles the problem of achieving group fairness in machine learning models without prior demographic information, proposing a method called VFair that minimizes variance of training losses to promote fairness while preserving utility, with experiments showing significant fairness improvements in regression tasks but not in classification tasks.
Due to privacy and security concerns, recent advancements in group fairness advocate for model training regardless of demographic information. However, most methods still require prior knowledge of demographics. In this study, we explore the potential for achieving fairness without compromising its utility when no prior demographics are provided to the training set, namely \emph{harmless Rawlsian fairness}. We ascertain that such a fairness requirement with no prior demographic information essential promotes training losses to exhibit a Dirac delta distribution. To this end, we propose a simple but effective method named VFair to minimize the variance of training losses inside the optimal set of empirical losses. This problem is then optimized by a tailored dynamic update approach that operates in both loss and gradient dimensions, directing the model towards relatively fairer solutions while preserving its intact utility. Our experimental findings indicate that regression tasks, which are relatively unexplored from literature, can achieve significant fairness improvement through VFair regardless of any prior, whereas classification tasks usually do not because of their quantized utility measurements. The implementation of our method is publicly available at \url{https://github.com/wxqpxw/VFair}.