International Joint Conference On Theoretical Computer Science – Frontier of Algorithmic Wisdom

August 15-19, 2022, City University of Hong Kong, Hong Kong

 

Invited Speakers

Machine Learning and Formal Method


Adaptive Fairness Improvement based on Causality Analysis

Mengdi Zhang

Singapore Management University

Abstract:
Given a discriminating neural network, the problem of fairness improvement is to systematically reduce discrimination without significantly scarifies its performance (i.e., accuracy). Multiple categories of fairness improving methods have been proposed for neural networks, including pre-processing, in-processing and post-processing. Our empirical study however shows that these methods are not always effective (e.g., they may improve fairness by paying the price of huge accuracy drop) or even not helpful (e.g., they may even worsen both fairness and accuracy). In this work, we propose an approach which adaptively chooses the fairness improving method based on causality analysis. That is, we choose the method based on how the neurons and attributes responsible for unfairness are distributed among the input attributes and the hidden neurons. Our experimental evaluation shows that our approach is effective (i.e., always identify the best fairness improving method) and efficient (i.e., with an average time overhead of 5 minutes).

Bio:
Mengdi Zhang is a third year Ph.D candidate in Singapore Management University supervised under Prof Jun Sun. She holds a B.E in the University of Electronic Science and Technology of China. Her research interests are mainly on AI security, including machine learning interpretability and fairness testing.