Measure Twice, Cut Once: Quantifying Bias and Fairness in Deep Neural Networks
arXiv:2110.04397
Abstract
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.
References in corpus (13)
- Distilling the Knowledge in a Neural Network
- Language Models are Few-Shot Learners
- On the Opportunities and Risks of Foundation Models
- Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
- To prune, or not to prune: exploring the efficacy of pruning for model compression
- Fairness in Machine Learning: A Survey
- Comparative Experiments on Disambiguating Word Senses: An Illustration of the Role of Bias in Machine Learning
- What Do Compressed Deep Neural Networks Forget?
- Rethinking Spatial Dimensions of Vision Transformers
- Characterising Bias in Compressed Models
- Knapsack Pruning with Inner Distillation
- Evaluating Fairness Metrics in the Presence of Dataset Bias
- Towards a Measure of Individual Fairness for Deep Learning