Shapley-Value-Based Graph Sparsification for GNN Inference

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Akkas, Selahattin, Azad, Ariful
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911079455522816
author Akkas, Selahattin
Azad, Ariful
author_facet Akkas, Selahattin
Azad, Ariful
contents Graph sparsification is a key technique for improving inference efficiency in Graph Neural Networks by removing edges with minimal impact on predictions. GNN explainability methods generate local importance scores, which can be aggregated into global scores for graph sparsification. However, many explainability methods produce only non-negative scores, limiting their applicability for sparsification. In contrast, Shapley value based methods assign both positive and negative contributions to node predictions, offering a theoretically robust and fair allocation of importance by evaluating many subsets of graphs. Unlike gradient-based or perturbation-based explainers, Shapley values enable better pruning strategies that preserve influential edges while removing misleading or adversarial connections. Our approach shows that Shapley value-based graph sparsification maintains predictive performance while significantly reducing graph complexity, enhancing both interpretability and efficiency in GNN inference.
format Preprint
id arxiv_https___arxiv_org_abs_2507_20460
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Shapley-Value-Based Graph Sparsification for GNN Inference
Akkas, Selahattin
Azad, Ariful
Machine Learning
Artificial Intelligence
Graph sparsification is a key technique for improving inference efficiency in Graph Neural Networks by removing edges with minimal impact on predictions. GNN explainability methods generate local importance scores, which can be aggregated into global scores for graph sparsification. However, many explainability methods produce only non-negative scores, limiting their applicability for sparsification. In contrast, Shapley value based methods assign both positive and negative contributions to node predictions, offering a theoretically robust and fair allocation of importance by evaluating many subsets of graphs. Unlike gradient-based or perturbation-based explainers, Shapley values enable better pruning strategies that preserve influential edges while removing misleading or adversarial connections. Our approach shows that Shapley value-based graph sparsification maintains predictive performance while significantly reducing graph complexity, enhancing both interpretability and efficiency in GNN inference.
title Shapley-Value-Based Graph Sparsification for GNN Inference
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2507.20460