On Fairness of Medical Image Classification with Multiple Sensitive Attributes via Learning Orthogonal Representations
This addresses fairness for patients with multiple demographic attributes in clinical applications, representing an incremental advance as it extends existing fairness methods to handle multiple sensitive attributes in medical imaging.
The paper tackles the problem of unfairness in medical image classification when multiple sensitive attributes are present, proposing a method that enforces orthogonality between target and sensitive representations to achieve fairness, with experiments on the CheXpert dataset demonstrating its effectiveness.
Mitigating the discrimination of machine learning models has gained increasing attention in medical image analysis. However, rare works focus on fair treatments for patients with multiple sensitive demographic ones, which is a crucial yet challenging problem for real-world clinical applications. In this paper, we propose a novel method for fair representation learning with respect to multi-sensitive attributes. We pursue the independence between target and multi-sensitive representations by achieving orthogonality in the representation space. Concretely, we enforce the column space orthogonality by keeping target information on the complement of a low-rank sensitive space. Furthermore, in the row space, we encourage feature dimensions between target and sensitive representations to be orthogonal. The effectiveness of the proposed method is demonstrated with extensive experiments on the CheXpert dataset. To our best knowledge, this is the first work to mitigate unfairness with respect to multiple sensitive attributes in the field of medical imaging.