Saved in:
Bibliographic Details
Main Author: Moradi, Ehsan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.27655
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917052876324864
author Moradi, Ehsan
author_facet Moradi, Ehsan
contents Feature-attribution methods (e.g., SHAP, LIME) explain individual predictions but often miss higher-order structure: sets of features that act in concert. We propose Modules of Influence (MoI), a framework that (i) constructs a model explanation graph from per-instance attributions, (ii) applies community detection to find feature modules that jointly affect predictions, and (iii) quantifies how these modules relate to bias, redundancy, and causality patterns. Across synthetic and real datasets, MoI uncovers correlated feature groups, improves model debugging via module-level ablations, and localizes bias exposure to specific modules. We release stability and synergy metrics, a reference implementation, and evaluation protocols to benchmark module discovery in XAI.
format Preprint
id arxiv_https___arxiv_org_abs_2510_27655
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Community Detection on Model Explanation Graphs for Explainable AI
Moradi, Ehsan
Social and Information Networks
Artificial Intelligence
Feature-attribution methods (e.g., SHAP, LIME) explain individual predictions but often miss higher-order structure: sets of features that act in concert. We propose Modules of Influence (MoI), a framework that (i) constructs a model explanation graph from per-instance attributions, (ii) applies community detection to find feature modules that jointly affect predictions, and (iii) quantifies how these modules relate to bias, redundancy, and causality patterns. Across synthetic and real datasets, MoI uncovers correlated feature groups, improves model debugging via module-level ablations, and localizes bias exposure to specific modules. We release stability and synergy metrics, a reference implementation, and evaluation protocols to benchmark module discovery in XAI.
title Community Detection on Model Explanation Graphs for Explainable AI
topic Social and Information Networks
Artificial Intelligence
url https://arxiv.org/abs/2510.27655