Faire: Repairing Fairness of Neural Networks via Neuron Condition Synthesis

作者：Tianlin Li, Xiaofei Xie, Jian Wang, Qing Guo, Aishan Liu, Lei Ma, Yang Liu · 发表于：ACM Transactions on Software Engineering and Methodology · 年份：2023 · DOI：10.1145/3617168 · 被引用次数：15 · 研究领域：Adversarial Robustness in Machine Learning、Explainable Artificial Intelligence (XAI)、Ethics and Social Impacts of AI

Deep Neural Networks (DNNs) have achieved tremendous success in many applications, while it has been demonstrated that DNNs can exhibit some undesirable behaviors on concerns such as robustness, privacy, and other trustworthiness issues. Among them, fairness (i.e., non-discrimination) is one important property, especially when they are applied to some sensitive applications (e.g., finance and employment). However, DNNs easily learn spurious correlations between protected attributes (e.g., age, gender, race) and the classification task and develop discriminatory behaviors if the training data is imbalanced. Such discriminatory decisions in sensitive applications would introduce severe social impacts. To expose potential discrimination problems in DNNs before putting them in use, some testing techniques have been proposed to identify the discriminatory instances (i.e., instances that show defined discrimination 1 ). However, how to repair DNNs after detecting such discrimination is still challenging. Existing techniques mainly rely on retraining on a large number of discriminatory instances generated by testing methods, which requires huge time overhead and makes the repairing inefficient. In this work, we propose the method Faire to effectively and efficiently repair the fairness issues of DNNs, without using additional data (e.g., discriminatory instances). Our basic idea is inspired by the traditional program repair method that synthesizes proper condition checking. To repai...