Getting a CLUE: A Method for Explaining Uncertainty Estimates
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.
Code (1)
Tasks
counterfactualMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates
To interpret uncertainty estimates from differentiable probabilistic models, recent work has proposed generating a single Counterfactual Latent Uncertainty Explanation (CLUE) for a given data point where the model is unc…
counterfactualDiversityMoleCLUEs: Molecular Conformers Maximally In-Distribution for Predictive Models
Structure-based molecular ML (SBML) models can be highly sensitive to input geometries and give predictions with large variance. We present an approach to mitigate the challenge of selecting conformations for such models…
counterfactualDecoderδ-CLUE: Diverse Sets of Explanations for Uncertainty Estimates
To interpret uncertainty estimates from differentiable probabilistic models, recent work has proposed generating Counterfactual Latent Uncertainty Explanations (CLUEs). However, for a single input, such approaches could …
counterfactualCLUE: Neural Networks Calibration via Learning Uncertainty-Error alignment
Reliable uncertainty estimation is critical for deploying neural networks (NNs) in real-world applications. While existing calibration techniques often rely on post-hoc adjustments or coarse-grained binning methods, they…
Language ModelingLanguage ModellingA Safe and Data-efficient Model-based Reinforcement Learning System for HVAC Control
Model-Based Reinforcement Learning (MBRL) has been widely studied for Heating, Ventilation, and Air Conditioning (HVAC) control in buildings. One of the critical challenges is the large amount of data required to effecti…
Model-based Reinforcement Learning