DeepAI AI Chat
Log In Sign Up

Leveraging Semi-Supervised Learning for Fairness using Neural Networks

by   Vahid Noroozi, et al.
Northwestern University
University of Illinois at Chicago

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.


page 1

page 2

page 3

page 4


Fairness Constraints in Semi-supervised Learning

Fairness in machine learning has received considerable attention. Howeve...

Fairness in Semi-supervised Learning: Unlabeled Data Help to Reduce Discrimination

A growing specter in the rise of machine learning is whether the decisio...

ClusterNet : Semi-Supervised Clustering using Neural Networks

Clustering using neural networks has recently demon- strated promising p...

Lidar-Camera Co-Training for Semi-Supervised Road Detection

Recent advances in the field of machine learning and computer vision hav...

RelationMatch: Matching In-batch Relationships for Semi-supervised Learning

Semi-supervised learning has achieved notable success by leveraging very...

Counterfactual Propagation for Semi-Supervised Individual Treatment Effect Estimation

Individual treatment effect (ITE) represents the expected improvement in...

Bringing Giant Neural Networks Down to Earth with Unlabeled Data

Compressing giant neural networks has gained much attention for their ex...