获得CLUE:一种解释不确定性估计的方法
Getting a CLUE: A Method for Explaining Uncertainty Estimates
摘要:
不确定性估计和可解释性是可信机器学习系统的重要因素。然而,在这两个领域的交叉点上几乎没有工作。我们提出了一种新的方法来解释从可微概率模型,如贝叶斯神经网络(BNN)的不确定性估计,以解决这个差距。我们的方法,反事实潜在不确定性消除(CLUE),指示如何改变输入,同时将其保持在数据流形上,使得BNN对输入的预测变得更加自信。我们通过1)一个新的框架来评估不确定性的反事实解释,2)一系列消融实验,和3)用户研究来验证CLUE。我们的实验表明,CLUE优于基线,使从业者能够更好地了解哪些输入模式是预测不确定性的原因。
英文摘要:
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.
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。