Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces
This addresses the need for responsible AI by simultaneously improving fairness, robustness, and causal awareness in classifiers, though it appears incremental as it combines existing concepts like causal models and adversarial training.
The paper tackles the problem of integrating individual fairness, adversarial robustness, and causality in machine learning for heterogeneous data with discrete sensitive attributes, resulting in a method that achieves an accurate classifier with these combined properties as demonstrated on real-world and synthetic datasets.
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.