Fairness and Explainability: Bridging the Gap towards Fair Model Explanations

While machine learning models have achieved unprecedented success in real-world applications, they might make biased/unfair decisions for specific demographic groups and hence result in discriminative outcomes. Although research efforts have been devoted to measuring and mitigating bias, they mainly study bias from the result-oriented perspective while neglecting the bias encoded in the decision-making procedure. This results in their inability to capture procedureoriented bias, which therefore limits the ability to have a fully debiasing method. Fortunately, with the rapid development of explainable machine learning, explanations for predictions are now available to gain insights into the procedure. In this work, we bridge the gap between fairness and explainability by presenting a novel perspective of procedure-oriented fairness based on explanations. We identify the procedurebased bias by measuring the gap of explanation quality between different groups with Ratio-based and Value-based Explanation Fairness. The new metrics further motivate us to design an optimization objective to mitigate the procedurebased bias where we observe that it will also mitigate bias from the prediction. Based on our designed optimization objective, we propose a Comprehensive Fairness Algorithm (CFA), which simultaneously fulfills multiple objectives -improving traditional fairness, satisfying explanation fairness, and maintaining the utility performance. Extensive experiments on real-world datasets demonstrate the effectiveness of our proposed CFA and highlight the importance of considering fairness from the explainability perspective. Our code: https://github.com/YuyingZhao/FairExplanations-CFA . Recent years have witnessed the unprecedented success of applying machine learning (ML) models in real-world domains, such as improving the efficiency of information retrieval (Fu et al. 2021; Wang et al. 2022b) and providing convenience with intelligent language translation (Dong et al. 2015) . However, recent studies have revealed that historical data may include patterns of previous discriminatory decisions dominated by sensitive features such as gender, age,