Learning Smooth and Fair Representations

06/15/2020
by   Xavier Gitiaux, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/06/2019

Flexibly Fair Representation Learning by Disentanglement

We consider the problem of learning representations that achieve group a...
research
01/11/2021

Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation

Controlling bias in training datasets is vital for ensuring equal treatm...
research
10/30/2019

DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning

We introduce a framework for dynamic adversarial discovery of informatio...
research
12/17/2018

BriarPatches: Pixel-Space Interventions for Inducing Demographic Parity

We introduce the BriarPatch, a pixel-space intervention that obscures se...
research
05/28/2021

Fair Representations by Compression

Organizations that collect and sell data face increasing scrutiny for th...
research
06/05/2023

Fair Patient Model: Mitigating Bias in the Patient Representation Learned from the Electronic Health Records

Objective: To pre-train fair and unbiased patient representations from E...
research
01/17/2022

Fair Group-Shared Representations with Normalizing Flows

The issue of fairness in machine learning stems from the fact that histo...

Please sign up or login with your details

Forgot password? Click here to reset