Distribution Contrast for Disentangled Fair Representation

• 발행기관: 한국자료분석학회
• 저자명: Changdae Oh Heeji Won Junhyuk So Taero Kim Yewon Kim Hosik Choi Kyungwoo Song
• 간행물 정보: 『한국자료분석학회 학술대회자료집』2022년 하계학술대회 발표집, 52~52쪽, 전체 1쪽
• 주제분류: 자연과학 > 통계학
• 파일형태: PDF
• 발행일자: 2022.07.07

영문 초록

Learning fair representation is crucial for achieving fairness or debiasing sensitive information. Most existing works rely on adversarial representation learning to inject some invariance into representation. However, adversarial learning methods are known to suffer from relatively unstable training, and this might harm the balance between fairness and predictiveness of representation. We propose a new approach, learning FAir Representation via distributional CONtrastive Variational AutoEncoder (FarconVAE), which induces the latent space to be disentangled into sensitive and nonsensitive parts. We first construct the pair of observations with different sensitive attributes but with the same labels. Then, FarconVAE enforces each non-sensitive latent to be closer, while sensitive latents to be far from each other and also far from the non-sensitive latent by contrasting their distributions. We provide a new type of contrastive loss motivated by Gaussian and Student-t kernels for distributional contrastive learning with theoretical analysis. Besides, we adopt a new swap-reconstruction loss to boost the disentanglement further. FarconVAE shows superior performance on fairness, pretrained model debiasing, and domain generalization tasks from various modalities, including tabular, image, and text.

키워드

Fairness Disentanglement Invariant Learning Contrastive Learning Variational Autoencoder