arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.01464cs.LGcs.AIstat.ML
收藏

存在抑制变量时 XAI 方法的理论行为

Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables

Technische Universität(柏林工业大学);Physikalisch-Technische Bundesanstalt(德国联邦物理技术研究院);Charité – Universitätsmedizin(夏里特医学院)

Rick Wilming, Leo Kieslich, Benedict Clark, Stefan Haufe

AI总结:

本文通过二维高斯二分类模型推导多种流行 XAI 方法的解析行为,证明相关噪声会使其错误地赋予无关抑制特征非零重要性,从而揭示解释可靠性的理论局限。

摘要:

近年来,“可解释人工智能”(XAI)社区提出了大量方法,以弥合模型“复杂性”与“可解释性”之间被认为存在的鸿沟。然而,XAI 方法所要解决的具体问题尚未得到形式化表述。因此,XAI 方法的解释“正确性”缺乏理论和实证证据,限制了其在质量控制和透明度目的上的潜在应用。与此同时,Haufe 等人(2014)通过简单的玩具示例表明,即使是线性模型的标准解释也可能具有高度误导性。具体而言,高重要性可能被归于所谓的抑制变量,而这些变量与预测目标之间不存在任何统计关系。Wilming 等人(2022)已在大量 XAI 方法上实证确认了这种行为。在此,我们更进一步:针对一个涉及高斯类条件分布的简单二维二分类问题,推导了多种流行 XAI 方法行为的解析表达式。我们表明,在存在相关噪声的情况下,所研究的大多数方法都会将非零重要性归于一个与类别无关的抑制特征。这对这些 XAI 方法输出所能支持的解释和结论构成了重要限制。

英文摘要:

In recent years, the community of 'explainable artificial intelligence' (XAI) has created a vast body of methods to bridge a perceived gap between model 'complexity' and 'interpretability'. However, a concrete problem to be solved by XAI methods has not yet been formally stated. As a result, XAI methods are lacking theoretical and empirical evidence for the 'correctness' of their explanations, limiting their potential use for quality-control and transparency purposes. At the same time, Haufe et al. (2014) showed, using simple toy examples, that even standard interpretations of linear models can be highly misleading. Specifically, high importance may be attributed to so-called suppressor variables lacking any statistical relation to the prediction target. This behavior has been confirmed empirically for a large array of XAI methods in Wilming et al. (2022). Here, we go one step further by deriving analytical expressions for the behavior of a variety of popular XAI methods on a simple two-dimensional binary classification problem involving Gaussian class-conditional distributions. We show that the majority of the studied approaches will attribute non-zero importance to a non-class-related suppressor feature in the presence of correlated noise. This poses important limitations on the interpretations and conclusions that the outputs of these XAI methods can afford.

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。

↑