Towards a Measure of Individual Fairness for Deep Learning
arXiv:2009.13650
Abstract
Deep learning has produced big advances in artificial intelligence, but trained neural networks often reflect and amplify bias in their training data, and thus produce unfair predictions. We propose a novel measure of individual fairness, called prediction sensitivity, that approximates the extent to which a particular prediction is dependent on a protected attribute. We show how to compute prediction sensitivity using standard automatic differentiation capabilities present in modern deep learning frameworks, and present preliminary empirical results suggesting that prediction sensitivity may be effective for measuring bias in individual predictions.
arXiv commentPresented at MD4SG '20
References in corpus (12)
- Equality of Opportunity in Supervised Learning
- Understanding deep learning requires rethinking generalization
- Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
- AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
- No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World
- Learning Non-Discriminatory Predictors
- On Formalizing Fairness in Prediction with Machine Learning
- Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction
- A Reductions Approach to Fair Classification
- A statistical framework for fair predictive algorithms
- Improved Adversarial Learning for Fair Classification
- The Case for Evaluating Causal Models Using Interventional Measures and Empirical Data