Measure Twice, Cut Once: Quantifying Bias and Fairness in Deep Neural Networks

Algorithmic bias is of increasing concern, both to the research community, and society at large. Bias in AI is more abstract and unintuitive than traditional forms of discrimination and can be more difficult to detect and mitigate. A clear gap exists in the current literature on evaluating the relative bias in the performance of multi-class classifiers. In this work, we propose two simple yet effective metrics, Combined Error Variance (CEV) and Symmetric Distance Error (SDE), to quantitatively evaluate the class-wise bias of two models in comparison to one another. By evaluating the performance of these new metrics and by demonstrating their practical application, we show that they can be used to measure fairness as well as bias. These demonstrations show that our metrics can address specific needs for measuring bias in multi-class classification. Broad acceptance of the large-scale deployment of AI and neural networks depends on the models' perceived trustworthiness and fairness. However, research on evaluating and mitigating bias for neural networks in general and compressed neural networks in particular is still in its infancy. Because deep neural networks (DNNs) are "black box" learners, it can be difficult to understand what correlations they have learned from their training data, and how that affects the downstream decisions that are made in the real world. Two models may appear to have very similar performance when only measured in terms of accuracy, precision, etc. but deeper analysis can show uneven performance across many classes.