Structural Compactness as a Complementary Criterion for Explanation Quality
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914434327248896 |
|---|---|
| author | Mesgari, Mohammad Mahdi Ma, Jackie Samek, Wojciech Lapuschkin, Sebastian Weber, Leander |
| author_facet | Mesgari, Mohammad Mahdi Ma, Jackie Samek, Wojciech Lapuschkin, Sebastian Weber, Leander |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_29491 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Structural Compactness as a Complementary Criterion for Explanation Quality Mesgari, Mohammad Mahdi Ma, Jackie Samek, Wojciech Lapuschkin, Sebastian Weber, Leander Artificial Intelligence 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. |
| title | Structural Compactness as a Complementary Criterion for Explanation Quality |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2603.29491 |