衡量基于概念的解释的（不）忠实性
Measuring the (Un)Faithfulness of Concept-Based Explanations
提出 SURF 代理模型和忠实性度量，为评估概念解释方法提供可靠基准，可指导视觉模型可解释性研究中选择更忠实的解释方法。
原文依据 We propose Surrogate Faithfulness (SURF), which (1) replaces prior complex surrogates with a simple, linear surrogate that measures faithfulness without changing the explanation's interpretability
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论深度视觉模型执行难以解释的输入-输出计算。基于概念的解释方法（CBEMs）通过用人类可理解的语义单元（即概念）重新表达模型的部分内容来提高可解释性。检查所得到的解释是否忠实——即是否表示模型的内部计算——需要一个结合概念来计算输出的代理模型。为可解释性所做的简化不可避免地会降低忠实性，从而导致两者之间的权衡。最优的无监督CBEMs（U-CBEMs）似乎更具可解释性，同时对模型也更忠实。然而，我们观察到，所报告的忠实性改进实际上源于以下两种情况之一：（1）使用过于复杂的代理模型，这给解释的可解释性带来了未被测量的成本；或（2）依赖基于删除的方法，而我们证明这些方法不能正确衡量忠实性。我们提出了代理忠实性（SURF），它（1）用简单的线性代理模型取代先前复杂的代理模型，在不改变解释可解释性的情况下衡量忠实性；（2）引入了有充分动机的度量，评估所有输出类别上的损失，而不仅仅是预测类别。我们通过提出一个简单的健全性检查——使用随机概念的解释应该更不忠实——来验证SURF，而先前的代理模型未能通过该检查。SURF实现了首个可靠的U-CBEMs忠实性基准，揭示了许多视觉上引人注目的U-CBEMs并不忠实。代码已发布。
英文原文摘要 1611 字符
Deep vision models perform input-output computations that are hard to interpret. Concept-based explanation methods (CBEMs) increase interpretability by re-expressing parts of the model with human-understandable semantic units, or concepts. Checking if the derived explanations are faithful--that is, they represent the model's internal computation--requires a surrogate that combines concepts to compute the output. Simplifications made for interpretability inevitably reduce faithfulness, resulting in a tradeoff between the two. State-of-the-art unsupervised CBEMs (U-CBEMs) are seemingly more interpretable, while also being more faithful to the model. However, we observe that the reported improvement in faithfulness artificially results from either (1) using overly complex surrogates, which introduces an unmeasured cost to the explanation's interpretability, or (2) relying on deletion-based approaches that, as we demonstrate, do not properly measure faithfulness. We propose Surrogate Faithfulness (SURF), which (1) replaces prior complex surrogates with a simple, linear surrogate that measures faithfulness without changing the explanation's interpretability and (2) introduces well-motivated metrics that assess loss across all output classes, not just the predicted class. We validate SURF with a measure-over-measure study by proposing a simple sanity check--explanations with random concepts should be less faithful-which prior surrogates fail. SURF enables the first reliable faithfulness benchmark of U-CBEMs, revealing that many visually compelling U-CBEMs are not faithful. Code is released.