论文标题
部分可观测时空混沌系统的无模型预测
Adaptive Fairness Improvement Based on Causality Analysis
论文作者
论文摘要
鉴于神经网络有区别，公平性改善的问题是系统地减少歧视而不会显着刺激其性能（即准确性）。已经提出了针对神经网络的多种公平改进方法，包括预处理，处理和后处理。然而，我们的实证研究表明，这些方法并不总是有效的（例如，它们可以通过支付巨大准确性下降的价格来提高公平性），甚至没有帮助（例如，它们甚至可能会使公平性和准确性恶化）。在这项工作中，我们提出了一种基于因果分析的公平性改进方法的方法。也就是说，我们根据如何在输入属性和隐藏的神经元之间分布的神经元和属性如何选择方法。我们的实验评估表明，我们的方法是有效的（即，始终确定最佳的公平性改善方法）和有效的效率（即，平均时间开销为5分钟）。
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).
