Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation

TL;DR

The paper introduces a simple, controllable feature whitening method that effectively reduces bias in neural networks by removing linear correlations, improving fairness without complex regularization or adversarial training.

Contribution

It proposes a novel feature whitening framework that mitigates bias by eliminating linear correlations, handling multiple fairness criteria, and outperforming existing methods on benchmark datasets.

Findings

Significantly reduces bias in neural networks.

Effectively handles demographic parity and equalized odds.

Outperforms existing bias mitigation methods on four datasets.

Abstract

As the use of artificial intelligence rapidly increases, the development of trustworthy artificial intelligence has become important. However, recent studies have shown that deep neural networks are susceptible to learn spurious correlations present in datasets. To improve the reliability, we propose a simple yet effective framework called controllable feature whitening. We quantify the linear correlation between the target and bias features by the covariance matrix, and eliminate it through the whitening module. Our results systemically demonstrate that removing the linear correlations between features fed into the last linear classifier significantly mitigates the bias, while avoiding the need to model intractable higher-order dependencies. A particular advantage of the proposed method is that it does not require regularization terms or adversarial learning, which often leads to unstable optimization in practice. Furthermore, we show that two fairness criteria, demographic parity and equalized odds, can be effectively handled by whitening with the re-weighted covariance matrix. Consequently, our method controls the trade-off between the utility and fairness of algorithms by adjusting the weighting coefficient. Finally, we validate that our method outperforms existing approaches on four benchmark datasets: Corrupted CIFAR-10, Biased FFHQ, WaterBirds, and Celeb-A.