Learning Smooth and Fair Representations
Organizations that own data face increasing legal liability for its discriminatory use against protected demographic groups, extending to contractual transactions involving third parties access and use of the data. This is problematic, since the original data owner cannot ex-ante anticipate all its future uses by downstream users. This paper explores the upstream ability to preemptively remove the correlations between features and sensitive attributes by mapping features to a fair representation space. Our main result shows that the fairness measured by the demographic parity of the representation distribution can be certified from a finite sample if and only if the chi-squared mutual information between features and representations is finite. Empirically, we find that smoothing the representation distribution provides generalization guarantees of fairness certificates, which improves upon existing fair representation learning approaches. Moreover, we do not observe that smoothing the representation distribution degrades the accuracy of downstream tasks compared to state-of-the-art methods in fair representation learning.
Code (0)
등록된 구현이 없습니다.
Tasks
FairnessRepresentation LearningSimilar Papers 제목 키워드 기반
Latent Space Smoothing for Individually Fair Representations
Fair representation learning transforms user data into a representation that ensures fairness and utility regardless of the downstream application. However, learning individually fair representations, i.e., guaranteeing …
FairnessRepresentation LearningFairness-aware Message Passing for Graph Neural Networks
Graph Neural Networks (GNNs) have shown great power in various domains. However, their predictions may inherit societal biases on sensitive attributes, limiting their adoption in real-world applications. Although many ef…
FairnessInput-agnostic Certified Group Fairness via Gaussian Parameter Smoothing
Only recently, researchers attempt to provide classification algorithms with provable group fairness guarantees. Most of these algorithms suffer from harassment caused by the requirement that the training and deployment …
FairnessTowards Auditability for Fairness in Deep Learning
Group fairness metrics can detect when a deep learning model behaves differently for advantaged and disadvantaged groups, but even models that score well on these metrics can make blatantly unfair predictions. We present…
Deep LearningFairnessPredictionSensitivityFair Representations by Compression
Organizations that collect and sell data face increasing scrutiny for the discriminatory use of data. We propose a novel unsupervised approach to transform data into a compressed binary representation independent of sens…
DecoderFairness