Learning Fairness from Demonstrations via Inverse Reinforcement Learning

Defining fairness in algorithmic contexts is challenging, particularly when adapting to new domains. Our research introduces a novel method for learning and applying group fairness preferences across different classification domains, without the need for manual fine-tuning. Utilizing concepts from inverse reinforcement learning (IRL), our approach enables the extraction and application of fairness preferences from human experts or established algorithms. We propose the first technique for using IRL to recover and adapt group fairness preferences to new domains, offering a low-touch solution for implementing fair classifiers in settings where expert-established fairness tradeoffs are not yet defined.