用图结构度量解释的紧凑性，更好区分不同方法的效果。
Structural Compactness as a Complementary Criterion for Explanation Quality
- 基于最小生成树构造紧凑性指标，捕捉高阶几何特征。
- 能有效区分不同解释方法，揭示模型间结构差异。
- 适合评估可解释性方法的可视化质量，尤其关注空间分布。
在解释质量的量化评估中，解释的可读性难以衡量，因其形状和内部组织复杂，无法通过简单统计捕捉。为此，我们提出最小生成树紧凑性（MST-C），一种基于图结构的度量方法，能够捕捉解释的传播与凝聚等高阶几何特性。该指标将这些特性融合为单一得分，偏好显著点集中且形成少数紧密簇的解释。实验表明，MST-C能可靠区分不同解释方法，揭示模型间的根本结构差异，并提供一个独立、稳健的解释紧凑性诊断工具，补充现有属性复杂度的概念。
原文摘要 · Abstract (English)
In the evaluation of attribution quality, the quantitative assessment of explanation legibility is particularly difficult, as it is influenced by varying shapes and internal organization of attributions not captured by simple statistics. To address this issue, we introduce Minimum Spanning Tree Compactness (MST-C), a graph-based structural metric that captures higher-order geometric properties of attributions, such as spread and cohesion. These components are combined into a single score that evaluates compactness, favoring attributions with salient points spread across a small area and spatially organized into few but cohesive clusters. We show that MST-C reliably distinguishes between explanation methods, exposes fundamental structural differences between models, and provides a robust, self-contained diagnostic for explanation compactness that complements existing notions of attribution complexity.
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。