AICYSep 28, 2020

Towards a Measure of Individual Fairness for Deep Learning

arXiv:2009.13650v16 citations
Originality Incremental advance
AI Analysis

This addresses fairness issues in AI for affected individuals, but it is incremental as it builds on existing fairness concepts.

The paper tackles the problem of bias in deep learning predictions by proposing a novel measure called prediction sensitivity, which approximates how much a prediction depends on a protected attribute, and shows preliminary empirical results suggesting its effectiveness.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes