Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AI
This work addresses the need for trustworthier AI by providing more reliable explanations, though it appears incremental as it builds on existing uncertainty quantification methods.
The paper tackles the problem of model transparency by using prediction uncertainty to improve explanation robustness, distinguishing between aleatoric and epistemic uncertainty to guide explanation selection and rejection.
Recent advancements in machine learning have emphasized the need for transparency in model predictions, particularly as interpretability diminishes when using increasingly complex architectures. In this paper, we propose leveraging prediction uncertainty as a complementary approach to classical explainability methods. Specifically, we distinguish between aleatoric (data-related) and epistemic (model-related) uncertainty to guide the selection of appropriate explanations. Epistemic uncertainty serves as a rejection criterion for unreliable explanations and, in itself, provides insight into insufficient training (a new form of explanation). Aleatoric uncertainty informs the choice between feature-importance explanations and counterfactual explanations. This leverages a framework of explainability methods driven by uncertainty quantification and disentanglement. Our experiments demonstrate the impact of this uncertainty-aware approach on the robustness and attainability of explanations in both traditional machine learning and deep learning scenarios.