arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2112.02646cs.LGcs.AIcs.CYstat.ML
收藏

不确定性估计的多样性、全球性和摊销的反事实假设

Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates

University of Cambridge(剑桥大学);The Alan Turing Institute(艾伦·图灵研究所)

Dan Ley, Umang Bhatt, Adrian Weller

摘要:

为了解释来自可微概率模型的不确定性估计,最近的工作提出了针对模型不确定的给定数据点生成单个反事实潜在不确定性解释(CLUE),识别输入的单个流形上变化,使得模型在其预测中变得更加确定。我们扩大探索,以检查$δ$ -线索,潜在的CLUE内的一个$δ$球的原始输入在潜在空间。我们研究了这些集合的多样性,发现许多CLUE是冗余的;因此,我们提出了DIVerse CLUE($\nabla$ -CLUE),一组CLUE,每个CLUE都提出了一个不同的解释,说明如何减少与输入相关的不确定性。然后,我们进一步提出了全球摊销的CLUE(GLAM-CLUE),一个独特的和新颖的方法,学习摊销的映射特定组的不确定的输入,采取他们和有效地将它们在一个单一的函数调用到输入的模型将是肯定的。我们的实验表明,$δ$,$\nabla$ -CLUE和GLAM-CLUE都解决了CLUE的缺点,并为从业者提供了有益的解释不确定性估计。

英文摘要:

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 uncertain, identifying a single, on-manifold change to the input such that the model becomes more certain in its prediction. We broaden the exploration to examine $δ$-CLUE, the set of potential CLUEs within a $δ$ ball of the original input in latent space. We study the diversity of such sets and find that many CLUEs are redundant; as such, we propose DIVerse CLUE ($\nabla$-CLUE), a set of CLUEs which each propose a distinct explanation as to how one can decrease the uncertainty associated with an input. We then further propose GLobal AMortised CLUE (GLAM-CLUE), a distinct and novel method which learns amortised mappings on specific groups of uncertain inputs, taking them and efficiently transforming them in a single function call into inputs for which a model will be certain. Our experiments show that $δ$-CLUE, $\nabla$-CLUE, and GLAM-CLUE all address shortcomings of CLUE and provide beneficial explanations of uncertainty estimates to practitioners.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑