Fairness in Deep Learning: A Computational Perspective
It tackles fairness issues in deep learning for high-stakes applications, but it is incremental as it provides a review rather than new results.
The paper reviews recent progress in addressing algorithmic fairness in deep learning, focusing on computational methods to diagnose and mitigate discrimination, with the goal of building fair and reliable systems.
Deep learning is increasingly being used in high-stake decision making applications that affect individual lives. However, deep learning models might exhibit algorithmic discrimination behaviors with respect to protected groups, potentially posing negative impacts on individuals and society. Therefore, fairness in deep learning has attracted tremendous attention recently. We provide a review covering recent progresses to tackle algorithmic fairness problems of deep learning from the computational perspective. Specifically, we show that interpretability can serve as a useful ingredient to diagnose the reasons that lead to algorithmic discrimination. We also discuss fairness mitigation approaches categorized according to three stages of deep learning life-cycle, aiming to push forward the area of fairness in deep learning and build genuinely fair and reliable deep learning systems.