Leveraging Semi-Supervised Learning for Fairness using Neural Networks

TL;DR

This paper introduces SSFair, a semi-supervised neural network algorithm that leverages unlabeled data to enhance both the performance and fairness of machine learning decision systems, addressing bias and data scarcity.

Contribution

The paper presents a novel semi-supervised approach that uses neural networks to improve fairness in decision-making by mitigating bias from unlabeled data.

Findings

Improves fairness by reducing bias in training data.

Enhances model performance with unlabeled data.

Demonstrates effectiveness of semi-supervised learning for fairness.

Abstract

There has been a growing concern about the fairness of decision-making systems based on machine learning. The shortage of labeled data has been always a challenging problem facing machine learning based systems. In such scenarios, semi-supervised learning has shown to be an effective way of exploiting unlabeled data to improve upon the performance of model. Notably, unlabeled data do not contain label information which itself can be a significant source of bias in training machine learning systems. This inspired us to tackle the challenge of fairness by formulating the problem in a semi-supervised framework. In this paper, we propose a semi-supervised algorithm using neural networks benefiting from unlabeled data to not just improve the performance but also improve the fairness of the decision-making process. The proposed model, called SSFair, exploits the information in the unlabeled data to mitigate the bias in the training data.