Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces

TL;DR

This paper introduces a novel method that integrates individual fairness, adversarial robustness, and causal reasoning in classifiers dealing with heterogeneous data, especially with discrete sensitive attributes, through causal adversarial perturbations and training.

Contribution

It proposes a new causal adversarial perturbation technique and regularizer that jointly optimize fairness, causality, and robustness in machine learning models.

Findings

Effective in achieving fairness, robustness, and causal awareness

Improves classifier performance on real-world datasets

Demonstrates advantages over existing methods

Abstract

As responsible AI gains importance in machine learning algorithms, properties such as fairness, adversarial robustness, and causality have received considerable attention in recent years. However, despite their individual significance, there remains a critical gap in simultaneously exploring and integrating these properties. In this paper, we propose a novel approach that examines the relationship between individual fairness, adversarial robustness, and structural causal models in heterogeneous data spaces, particularly when dealing with discrete sensitive attributes. We use causal structural models and sensitive attributes to create a fair metric and apply it to measure semantic similarity among individuals. By introducing a novel causal adversarial perturbation and applying adversarial training, we create a new regularizer that combines individual fairness, causality, and robustness in the classifier. Our method is evaluated on both real-world and synthetic datasets, demonstrating its effectiveness in achieving an accurate classifier that simultaneously exhibits fairness, adversarial robustness, and causal awareness.