Fairness in Deep Learning: A Computational Perspective

Abstract

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.

References in corpus (12)

• Equality of Opportunity in Supervised Learning
• Understanding Neural Networks Through Deep Visualization
• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
• On Formalizing Fairness in Prediction with Machine Learning
• Flexibly Fair Representation Learning by Disentanglement
• Compositional Fairness Constraints for Graph Embeddings
• InclusiveFaceNet: Improving Face Attribute Detection with Race and Gender Diversity
• Deep Learning for Face Recognition: Pride or Prejudiced?
• Wasserstein Fair Classification
• Auditing ImageNet: Towards a Model-driven Framework for Annotating Demographic Attributes of Large-Scale Image Datasets