面向需求驱动的视觉反事实解释器设计
Towards Desiderata-Driven Design of Visual Counterfactual Explainers
AI总结：
本文提出一种新的'平滑反事实探索器'算法，旨在通过优化反事实生成机制，提升视觉解释器在保真度、可理解性和充分性方面的综合性能。
摘要：
视觉反事实解释器（VCEs）是一种简单且有前景的方法，用于增强图像分类器的透明性。VCEs通过揭示机器学习模型最强烈响应的数据转换，补充了其他类型的解释，如特征归因。在本文中，我们主张现有的VCEs过于狭窄地优化样本质量和变化最小性；它们未能考虑解释的更全面的需求，如保真度、可理解性和充分性。为了解决这一不足，我们探索了反事实生成的新机制，并研究它们如何帮助满足这些需求。我们将这些机制结合成一种新的'平滑反事实探索器'（SCE）算法，并通过系统评估在合成和真实数据上展示了其有效性。
英文摘要：
Visual counterfactual explainers (VCEs) are a straightforward and promising approach to enhancing the transparency of image classifiers. VCEs complement other types of explanations, such as feature attribution, by revealing the specific data transformations to which a machine learning model responds most strongly. In this paper, we argue that existing VCEs focus too narrowly on optimizing sample quality or change minimality; they fail to consider the more holistic desiderata for an explanation, such as fidelity, understandability, and sufficiency. To address this shortcoming, we explore new mechanisms for counterfactual generation and investigate how they can help fulfill these desiderata. We combine these mechanisms into a novel 'smooth counterfactual explorer' (SCE) algorithm and demonstrate its effectiveness through systematic evaluations on synthetic and real data.
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。
