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 2302.11965cs.AI
收藏

解释的泛化性

The Generalizability of Explanations

TU Dortmund(多特蒙德大学);AI Group(人工智能集团)

Hanxiao Tan

AI总结:

本文提出从泛化性角度评估可解释性方法,利用自编码器学习解释分布并验证其可学习性,发现SmoothGrad平滑能显著提升解释的泛化能力。

摘要:

由于缺乏真实标签,对可解释性方法进行客观评估是一个重要的研究方向。迄今为止,绝大多数评估可以归纳为三类,即人工评估、敏感性测试和显著性检验。本文从泛化性的角度提出了一种新的评估方法。我们采用自编码器来学习所生成解释的分布,并观察其可学习性以及所学分布特征的可信度。我们首先在LIME上简要展示了所提方法的评估思路,然后定量评估了多种流行的可解释性方法。我们还发现,使用SmoothGrad对解释进行平滑处理可以显著增强解释的泛化性。

英文摘要:

Due to the absence of ground truth, objective evaluation of explainability methods is an essential research direction. So far, the vast majority of evaluations can be summarized into three categories, namely human evaluation, sensitivity testing, and salinity check. This work proposes a novel evaluation methodology from the perspective of generalizability. We employ an Autoencoder to learn the distributions of the generated explanations and observe their learnability as well as the plausibility of the learned distributional features. We first briefly demonstrate the evaluation idea of the proposed approach at LIME, and then quantitatively evaluate multiple popular explainability methods. We also find that smoothing the explanations with SmoothGrad can significantly enhance the generalizability of explanations.

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。

↑