paper-with-me

홈 › Papers

Learning Smooth and Fair Representations

2020-06-15 · Xavier Gitiaux, Huzefa Rangwala

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.

📄 PDF Abstract BibTeX arXiv:2006.08788

Code (0)

등록된 구현이 없습니다.

Tasks

FairnessRepresentation Learning

Similar Papers 제목 키워드 기반

Latent Space Smoothing for Individually Fair Representations

2021-11-26 · Momchil Peychev, Anian Ruoss, Mislav Balunović, Maximilian Baader 외

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 Learning

Fairness-aware Message Passing for Graph Neural Networks

2023-06-19 · Huaisheng Zhu, Guoji Fu, Zhimeng Guo, Zhiwei Zhang 외

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…

Fairness

Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothing

2022-06-22 · Jiayin Jin, Zeru Zhang, Yang Zhou, Lingfei Wu

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 …

Fairness

Towards Auditability for Fairness in Deep Learning

2020-11-30 · Ivoline C. Ngong, Krystal Maughan, Joseph P. Near

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 LearningFairnessPredictionSensitivity

Fair Representations by Compression

2021-05-28 · Xavier Gitiaux, Huzefa Rangwala

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