当稳定性遇上充分性：不会令人不堪重负的信息性解释
When Stability meets Sufficiency: Informative Explanations that do not Overwhelm
AI总结：
针对最小充分解释过于稀疏的问题，本文提出PSEM，生成从原始输入到最小充分解释的稳定递减解释路径，并在三种模态和用户研究中验证其效果。
摘要：
近期评估可解释人工智能（XAI）各类准则的研究表明，保真度、稳定性和可理解性是AI用户在多种使用场景中认为最重要的指标之一。我们将这些准则应用于基于特征的归因方法，这类方法是XAI文献中最普遍的方法之一。除标准相关性之外，已有方法被提出，用于突出证明输入分类所需的最低限度充分内容（即相关正样本）。尽管最低充分性是一种类似可理解性的有吸引力的属性，但由此产生的解释往往过于稀疏，以至于人类无法理解和评估模型的局部行为。为克服这些限制，我们纳入稳定性和保真度准则，并提出一种名为路径充分解释方法（Path-Sufficient Explanations Method，PSEM）的新方法。该方法针对给定输入输出一系列稳定且充分的解释，其大小（或值）严格递减——从原始输入到最低限度充分的解释——可以被认为以稳定方式描绘模型的局部边界，从而为特定输入的局部模型行为提供更好的直觉。我们通过实验在定性和定量上验证了这些主张；实验表明，PSEM在图像、表格和文本三种模态上均具有优势，并且优于其他路径解释。一项用户研究展示了该方法在传达局部行为方面的优势，其中（许多）用户能够正确判断模型所作出的预测。
英文摘要：
Recent studies evaluating various criteria for explainable artificial intelligence (XAI) suggest that fidelity, stability, and comprehensibility are among the most important metrics considered by users of AI across a diverse collection of usage contexts. We consider these criteria as applied to feature-based attribution methods, which are amongst the most prevalent in XAI literature. Going beyond standard correlation, methods have been proposed that highlight what should be minimally sufficient to justify the classification of an input (viz. pertinent positives). While minimal sufficiency is an attractive property akin to comprehensibility, the resulting explanations are often too sparse for a human to understand and evaluate the local behavior of the model. To overcome these limitations, we incorporate the criteria of stability and fidelity and propose a novel method called Path-Sufficient Explanations Method (PSEM) that outputs a sequence of stable and sufficient explanations for a given input of strictly decreasing size (or value) -- from original input to a minimally sufficient explanation -- which can be thought to trace the local boundary of the model in a stable manner, thus providing better intuition about the local model behavior for the specific input. We validate these claims, both qualitatively and quantitatively, with experiments that show the benefit of PSEM across three modalities (image, tabular and text) as well as versus other path explanations. A user study depicts the strength of the method in communicating the local behavior, where (many) users are able to correctly determine the prediction made by a model.
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。
