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.
翻译:为了解释不同概率模型的不确定性估计,最近的工作提议生成反事实迟疑性解释(CLUEs ) 。 但是,对于单一的投入,这种方法可以输出各种解释,因为解释缺乏限制。 我们在此增加原始CLUE方法, 以提供我们称之为$delta$-CLUE的CLUE方法。 CLUE 指出, $\it{one} $ 来改变输入, 同时保留在数据方块上, 使模型对其预测更加有信心。 我们更回回一个可信的CLUEs $( $\ delta$- CLUE ) : 多种不同的输入, 这些输入在潜在空间最初输入的$\delta$球内, 都产生自信的预测。