Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning
This addresses the need for explainable and actionable uncertainty quantification in AI systems to build trust, though it appears incremental as it builds on existing gradient-based and Bayesian methods.
The paper tackles the problem of explaining and mitigating prediction uncertainties in Bayesian deep learning by proposing a gradient-based uncertainty attribution method (UA-Backprop) to identify input regions contributing to uncertainty, and it shows competitive accuracy and efficiency with qualitative and quantitative evaluations.
Predictions made by deep learning models are prone to data perturbations, adversarial attacks, and out-of-distribution inputs. To build a trusted AI system, it is therefore critical to accurately quantify the prediction uncertainties. While current efforts focus on improving uncertainty quantification accuracy and efficiency, there is a need to identify uncertainty sources and take actions to mitigate their effects on predictions. Therefore, we propose to develop explainable and actionable Bayesian deep learning methods to not only perform accurate uncertainty quantification but also explain the uncertainties, identify their sources, and propose strategies to mitigate the uncertainty impacts. Specifically, we introduce a gradient-based uncertainty attribution method to identify the most problematic regions of the input that contribute to the prediction uncertainty. Compared to existing methods, the proposed UA-Backprop has competitive accuracy, relaxed assumptions, and high efficiency. Moreover, we propose an uncertainty mitigation strategy that leverages the attribution results as attention to further improve the model performance. Both qualitative and quantitative evaluations are conducted to demonstrate the effectiveness of our proposed methods.