FairFLRep: Fairness aware fault localization and repair of Deep Neural Networks

TL;DR

FairFLRep is an automated method that identifies and repairs biased neurons in deep neural networks, improving fairness in high-stakes applications while maintaining accuracy and efficiency.

Contribution

It introduces a novel fairness-aware fault localization and repair technique targeting bias-inducing neurons in DNNs, a significant advancement over existing methods.

Findings

Outperforms existing fairness repair methods in accuracy and fairness.

Effectively identifies neurons responsible for biased decisions.

More efficient than baseline approaches in repairing biases.

Abstract

Deep neural networks (DNNs) are being utilized in various aspects of our daily lives, including high-stakes decision-making applications that impact individuals. However, these systems reflect and amplify bias from the data used during training and testing, potentially resulting in biased behavior and inaccurate decisions. For instance, having different misclassification rates between white and black sub-populations. However, effectively and efficiently identifying and correcting biased behavior in DNNs is a challenge. This paper introduces FairFLRep, an automated fairness-aware fault localization and repair technique that identifies and corrects potentially bias-inducing neurons in DNN classifiers. FairFLRep focuses on adjusting neuron weights associated with sensitive attributes, such as race or gender, that contribute to unfair decisions. By analyzing the input-output relationships within the network, FairFLRep corrects neurons responsible for disparities in predictive quality parity. We evaluate FairFLRep on four image classification datasets using two DNN classifiers, and four tabular datasets with a DNN model. The results show that FairFLRep consistently outperforms existing methods in improving fairness while preserving accuracy. An ablation study confirms the importance of considering fairness during both fault localization and repair stages. Our findings also show that FairFLRep is more efficient than the baseline approaches in repairing the network.