ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule mining

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sharman, Bharat, Hassini, Elkafi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911291993489408
author Sharman, Bharat
Hassini, Elkafi
author_facet Sharman, Bharat
Hassini, Elkafi
contents Numerous graph neural network (GNN)-based algorithms have been proposed to solve graph-based combinatorial optimization problems (COPs), but methods to explain their predictions remain largely undeveloped. We introduce ARM-Explainer, a post-hoc, model-level explainer based on association rule mining, and demonstrate it on the predictions of the hybrid geometric scattering (HGS) GNN for the maximum clique problem (MCP), a canonical NP-hard graph-based COP. The eight most explanatory association rules discovered by ARM-Explainer achieve high median lift and confidence values of 2.42 and 0.49, respectively, on test instances from the TWITTER and BHOSLIB-DIMACS benchmark datasets. ARM-Explainer identifies the most important node features, together with their value ranges, that influence the GNN's predictions on these datasets. Furthermore, augmenting the GNN with informative node features substantially improves its performance on the MCP, increasing the median largest-found clique size by 22% (from 29.5 to 36) on large graphs from the BHOSLIB-DIMACS dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22866
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule mining
Sharman, Bharat
Hassini, Elkafi
Machine Learning
Optimization and Control
Numerous graph neural network (GNN)-based algorithms have been proposed to solve graph-based combinatorial optimization problems (COPs), but methods to explain their predictions remain largely undeveloped. We introduce ARM-Explainer, a post-hoc, model-level explainer based on association rule mining, and demonstrate it on the predictions of the hybrid geometric scattering (HGS) GNN for the maximum clique problem (MCP), a canonical NP-hard graph-based COP. The eight most explanatory association rules discovered by ARM-Explainer achieve high median lift and confidence values of 2.42 and 0.49, respectively, on test instances from the TWITTER and BHOSLIB-DIMACS benchmark datasets. ARM-Explainer identifies the most important node features, together with their value ranges, that influence the GNN's predictions on these datasets. Furthermore, augmenting the GNN with informative node features substantially improves its performance on the MCP, increasing the median largest-found clique size by 22% (from 29.5 to 36) on large graphs from the BHOSLIB-DIMACS dataset.
title ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule mining
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2511.22866