De-biased Representation Learning for Fairness with Unreliable Labels

by   Yixuan Zhang, et al.

Removing bias while keeping all task-relevant information is challenging for fair representation learning methods since they would yield random or degenerate representations w.r.t. labels when the sensitive attributes correlate with labels. Existing works proposed to inject the label information into the learning procedure to overcome such issues. However, the assumption that the observed labels are clean is not always met. In fact, label bias is acknowledged as the primary source inducing discrimination. In other words, the fair pre-processing methods ignore the discrimination encoded in the labels either during the learning procedure or the evaluation stage. This contradiction puts a question mark on the fairness of the learned representations. To circumvent this issue, we explore the following question: Can we learn fair representations predictable to latent ideal fair labels given only access to unreliable labels? In this work, we propose a De-Biased Representation Learning for Fairness (DBRF) framework which disentangles the sensitive information from non-sensitive attributes whilst keeping the learned representations predictable to ideal fair labels rather than observed biased ones. We formulate the de-biased learning framework through information-theoretic concepts such as mutual information and information bottleneck. The core concept is that DBRF advocates not to use unreliable labels for supervision when sensitive information benefits the prediction of unreliable labels. Experiment results over both synthetic and real-world data demonstrate that DBRF effectively learns de-biased representations towards ideal labels.


page 1

page 2

page 3

page 4


FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations

Bias in computer vision systems can perpetuate or even amplify discrimin...

An Information-Theoretic Perspective on the Relationship Between Fairness and Accuracy

Our goal is to understand the so-called trade-off between fairness and a...

FairMixRep : Self-supervised Robust Representation Learning for Heterogeneous Data with Fairness constraints

Representation Learning in a heterogeneous space with mixed variables of...

Fairness via Representation Neutralization

Existing bias mitigation methods for DNN models primarily work on learni...

Group Fairness by Probabilistic Modeling with Latent Fair Decisions

Machine learning systems are increasingly being used to make impactful d...

Learning Unbiased Representations via Rényi Minimization

In recent years, significant work has been done to include fairness cons...

Invariant Representations with Stochastically Quantized Neural Networks

Representation learning algorithms offer the opportunity to learn invari...

Please sign up or login with your details

Forgot password? Click here to reset