Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation
This addresses algorithmic bias issues in AI deployment, particularly for fairness-critical applications, but is incremental as it builds on existing pruning and distillation methods.
The paper tackles the problem of evaluating and mitigating bias in pruned neural networks, proposing metrics like Combined Error Variance and Symmetric Distance Error to measure bias, and showing that knowledge distillation reduces bias by up to 30% in some cases.
In recent years the ubiquitous deployment of AI has posed great concerns in regards to algorithmic bias, discrimination, and fairness. Compared to traditional forms of bias or discrimination caused by humans, algorithmic bias generated by AI is more abstract and unintuitive therefore more difficult to explain and mitigate. A clear gap exists in the current literature on evaluating and mitigating bias in pruned neural networks. In this work, we strive to tackle the challenging issues of evaluating, mitigating, and explaining induced bias in pruned neural networks. Our paper makes three contributions. First, we propose two simple yet effective metrics, Combined Error Variance (CEV) and Symmetric Distance Error (SDE), to quantitatively evaluate the induced bias prevention quality of pruned models. Second, we demonstrate that knowledge distillation can mitigate induced bias in pruned neural networks, even with unbalanced datasets. Third, we reveal that model similarity has strong correlations with pruning induced bias, which provides a powerful method to explain why bias occurs in pruned neural networks. Our code is available at https://github.com/codestar12/pruning-distilation-bias