arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.19683cs.LGcs.AI
收藏

重新审视事后可解释性方法的鲁棒性

Revisiting the robustness of post-hoc interpretability methods

National University of Singapore(新加坡国立大学);College of Design and Engineering(设计与工程学院);University of Geneva(日内瓦大学);University hospitals of Geneva(日内瓦大学医院)

Jiawen Wei, Hugues Turbé, Gianmarco Mengaldo

AI总结:

针对事后可解释性方法缺乏样本级细粒度评估的问题,提出一种新方法和两个新指标来评估其鲁棒性,并发现鲁棒性与粗粒度性能相关联。

摘要:

事后可解释性方法在可解释人工智能(XAI)中扮演着关键角色,因为它们能精确定位受过训练的深度学习模型在做出决策时认为重要的那部分数据。然而,不同的事后可解释性方法通常会给出不同的结果,这引发了人们对其准确性的怀疑。出于这个原因,人们已经提出了几种评估策略来理解事后可解释性的准确性。许多这样的评估策略提供了一种粗粒度的评估——也就是说,它们通过破坏多个样本中的不同数据点来评估模型性能平均是如何下降的。虽然这些策略在平均意义上选择最可靠的事后可解释性方法时是有效的,但它们无法提供样本级别的(也称为细粒度的)评估。换句话说,它们没有衡量事后可解释性方法的鲁棒性。我们提出了一种方法和两个新指标,以提供对事后可解释性方法的细粒度评估。我们表明,鲁棒性通常与其粗粒度性能相关联。

英文摘要:

Post-hoc interpretability methods play a critical role in explainable artificial intelligence (XAI), as they pinpoint portions of data that a trained deep learning model deemed important to make a decision. However, different post-hoc interpretability methods often provide different results, casting doubts on their accuracy. For this reason, several evaluation strategies have been proposed to understand the accuracy of post-hoc interpretability. Many of these evaluation strategies provide a coarse-grained assessment -- i.e., they evaluate how the performance of the model degrades on average by corrupting different data points across multiple samples. While these strategies are effective in selecting the post-hoc interpretability method that is most reliable on average, they fail to provide a sample-level, also referred to as fine-grained, assessment. In other words, they do not measure the robustness of post-hoc interpretability methods. We propose an approach and two new metrics to provide a fine-grained assessment of post-hoc interpretability methods. We show that the robustness is generally linked to its coarse-grained performance.

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。

↑