Work

On The Impact of Machine Learning Randomness on Group Fairness

Year: 2023

Type: conference-paper

Abstract: Statistical measures for group fairness in machine learning reflect the gap in performance of algorithms across different groups. These measures, however, exhibit a high variance between different training instances, which makes them unreliable for empirical evaluation of fairness. What causes this high variance? We investigate the impact on group fairness of different sources of randomness in training neural networks. We show that the variance in group fairness measures is rooted in the high volatility of the learning process on under-represented groups. Further, we recognize the dominant source of randomness as the stochasticity of data order during training. Based on these findings, we show how one can control group-level accuracy (i.e., model fairness), with high efficiency and negligible impact on the model’s overall performance, by simply changing the data order for a single epoch.

Source: ACM Conference on Fairness, Accountability, and Transparency (FAccT)

DOI: 10.1145/3593013.3594116

Authors: Prakhar Ganesh, Hongyan Chang, Martin Strobel, Reza Shokri

Institution: National University of Singapore

Language: English

Topic: Ethics and Social Impacts of AI

Subfield: Safety Research

Field: Social Sciences

Domain: Social Sciences

SDG: Reduced inequalities

Open Access status: hybrid

Funders: National Research Foundation, National Research Foundation Singapore