CUED Publications database

δ-CLUE: Diverse Sets of Explanations for Uncertainty Estimates

Ley, D and Bhatt, U and Weller, A δ-CLUE: Diverse Sets of Explanations for Uncertainty Estimates. (Unpublished)

Full text not available from this repository.

Abstract

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 output a variety of explanations due to the lack of constraints placed on the explanation. Here we augment the original CLUE approach, to provide what we call $\delta$-CLUE. CLUE indicates $\it{one}$ way to change an input, while remaining on the data manifold, such that the model becomes more confident about its prediction. We instead return a $\it{set}$ of plausible CLUEs: multiple, diverse inputs that are within a $\delta$ ball of the original input in latent space, all yielding confident predictions.

Item Type: Article
Uncontrolled Keywords: cs.LG cs.LG cs.AI stat.ML
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 16 Apr 2021 20:08
Last Modified: 20 May 2021 06:19
DOI: