Two Simple Ways to Learn Individual Fairness Metrics from Data

Abstract

Individual fairness is an intuitive definition of algorithmic fairness that addresses some of the drawbacks of group fairness. Despite its benefits, it depends on a task specific fair metric that encodes our intuition of what is fair and unfair for the ML task at hand, and the lack of a widely accepted fair metric for many ML tasks is the main barrier to broader adoption of individual fairness. In this paper, we present two simple ways to learn fair metrics from a variety of data types. We show empirically that fair training with the learned metrics leads to improved fairness on three machine learning tasks susceptible to gender and racial biases. We also provide theoretical guarantees on the statistical performance of both approaches.

To appear in ICML 2020

References in corpus (18)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Semantics derived automatically from language corpora contain human-like biases
• A Survey on Metric Learning for Feature Vectors and Structured Data
• On the (im)possibility of fairness
• Risk bounds for statistical learning
• Learning Adversarially Fair and Transferable Representations
• Understanding the Origins of Bias in Word Embeddings
• Attenuating Bias in Word Vectors
• Online Learning with an Unknown Fairness Metric
• Training individually fair ML models with Sensitive Subspace Robustness
• Fairness Through Awareness
• Probably Approximately Metric-Fair Learning
• Gender Bias in Contextualized Word Embeddings
• What's in a Name? Reducing Bias in Bios without Access to Protected Attributes
• An Empirical Study on Learning Fairness Metrics for COMPAS Data with Human Supervision
• A Tutorial on Distance Metric Learning: Mathematical Foundations, Algorithms, Experimental Analysis, Prospects and Challenges (with Appendices on Mathematical Background and Detailed Algorithms Explanation)
• Debiasing representations by removing unwanted variation due to protected attributes

Cited by in corpus (6)

• Learning Certified Individually Fair Representations
• SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness
• Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairness
• Black Loans Matter: Distributionally Robust Fairness for Fighting Subgroup Discrimination
• Gerrymandering Individual Fairness
• Individually Fair Ranking