Fairness-Driven Private Collaborative Machine Learning

TL;DR

This paper proposes a privacy-preserving pre-processing method to improve fairness in collaborative machine learning, enabling multiple parties to share data securely while reducing bias.

Contribution

It introduces a novel pre-process mechanism that enhances fairness in collaborative ML without significantly sacrificing accuracy.

Findings

Significantly improves fairness in collaborative ML

Maintains high accuracy with minor compromise

Applicable to sensitive domains like medicine and finance

Abstract

The performance of machine learning algorithms can be considerably improved when trained over larger datasets. In many domains, such as medicine and finance, larger datasets can be obtained if several parties, each having access to limited amounts of data, collaborate and share their data. However, such data sharing introduces significant privacy challenges. While multiple recent studies have investigated methods for private collaborative machine learning, the fairness of such collaborative algorithms was overlooked. In this work we suggest a feasible privacy-preserving pre-process mechanism for enhancing fairness of collaborative machine learning algorithms. Our experimentation with the proposed method shows that it is able to enhance fairness considerably with only a minor compromise in accuracy.