Getting a CLUE: A Method for Explaining Uncertainty Estimates
This addresses the problem of making uncertainty estimates interpretable for practitioners in trustworthy AI, though it is incremental as it builds on existing probabilistic models.
The authors tackled the lack of methods for interpreting uncertainty estimates in machine learning by proposing CLUE, a method that shows how to modify inputs to increase model confidence, validated through experiments and a user study.
Both uncertainty estimation and interpretability are important factors for trustworthy machine learning systems. However, there is little work at the intersection of these two areas. We address this gap by proposing a novel method for interpreting uncertainty estimates from differentiable probabilistic models, like Bayesian Neural Networks (BNNs). Our method, Counterfactual Latent Uncertainty Explanations (CLUE), indicates how to change an input, while keeping it on the data manifold, such that a BNN becomes more confident about the input's prediction. We validate CLUE through 1) a novel framework for evaluating counterfactual explanations of uncertainty, 2) a series of ablation experiments, and 3) a user study. Our experiments show that CLUE outperforms baselines and enables practitioners to better understand which input patterns are responsible for predictive uncertainty.