用因果理论生成更精准的图像分类解释。
Causal Explanations for Image Classifiers
- 基于实际因果理论构建黑盒解释框架。
- 实验表明解释更小且效率最高，质量优于现有工具。
- 适合需要可解释性与高效性的模型调试场景。
现有图像分类器解释算法采用多种定义和方法，但缺乏基于因果理论的严谨框架。本文提出一种基于实际因果理论的新型黑盒解释方法，证明了相关理论结果，并设计了近似解释计算算法。我们证明了算法的终止性，分析了复杂度及近似程度。通过实现工具ReX，实验对比显示，ReX是目前最高效的黑盒工具，生成的解释最小，且在标准评估指标上优于其他黑盒方法。
原文摘要 · Abstract (English)
Existing algorithms for explaining the output of image classifiers use different definitions of explanations and a variety of techniques to find them. However, none of the existing tools use a principled approach based on formal definitions of cause and explanation. In this paper we present a novel black-box approach to computing explanations grounded in the theory of actual causality. We prove relevant theoretical results and present an algorithm for computing approximate explanations based on these definitions. We prove termination of our algorithm and discuss its complexity and the amount of approximation compared to the precise definition. We implemented the framework in a tool ReX and we present experimental results and a comparison with state-of-the-art tools. We demonstrate that ReX is the most efficient black-box tool and produces the smallest explanations, in addition to outperforming other black-box tools on standard quality measures.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。