Adaptive Fairness Improvement Based on Causality Analysis
This work addresses fairness improvement in neural networks for applications where existing methods are ineffective or harmful, offering an adaptive solution to reduce discrimination.
The paper tackles the problem of improving fairness in neural networks without significantly sacrificing accuracy by proposing an adaptive method selection approach based on causality analysis, which effectively identifies the best fairness-improving method with an average time overhead of 5 minutes.
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).