用不确定性分解提升解释可信度，让AI决策更透明可靠。
Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AI
- 区分数据不确定性和模型不确定性，指导解释方法选择。
- 模型不确定性可作拒绝不可靠解释的依据，揭示训练不足。
- 适用于复杂模型，适合追求可信AI的研究者与开发者。
近年来机器学习的发展强调了模型预测透明性的重要性，尤其是在使用越来越复杂的架构时，传统可解释性方法的效力下降。本文提出将预测不确定性作为经典可解释性方法的补充。具体而言，我们区分了数据相关的意外不确定性（aleatoric）和模型相关的认知不确定性（epistemic），以指导解释方法的选择。认知不确定性可作为不可靠解释的拒绝标准，并自身提供对训练不足的洞察（一种新形式的解释）。意外不确定性则用于在特征重要性解释与反事实解释之间进行选择。该方法构建了一个由不确定性量化与解耦驱动的可解释性框架。实验表明，这种不确定性感知的方法在传统机器学习和深度学习场景中显著提升了解释的鲁棒性与可获得性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。