Back to Search Start Over

Generative Explanations for Graph Neural Network: Methods and Evaluations

Authors :
Chen, Jialin
Amara, Kenza
Yu, Junchi
Ying, Rex
Chen, Jialin
Amara, Kenza
Yu, Junchi
Ying, Rex
Publication Year :
2023

Abstract

Graph Neural Networks (GNNs) achieve state-of-the-art performance in various graph-related tasks. However, the black-box nature often limits their interpretability and trustworthiness. Numerous explainability methods have been proposed to uncover the decision-making logic of GNNs, by generating underlying explanatory substructures. In this paper, we conduct a comprehensive review of the existing explanation methods for GNNs from the perspective of graph generation. Specifically, we propose a unified optimization objective for generative explanation methods, comprising two sub-objectives: Attribution and Information constraints. We further demonstrate their specific manifestations in various generative model architectures and different explanation scenarios. With the unified objective of the explanation problem, we reveal the shared characteristics and distinctions among current methods, laying the foundation for future methodological advancements. Empirical results demonstrate the advantages and limitations of different explainability approaches in terms of explanation performance, efficiency, and generalizability.

Details

Database :
OAIster
Publication Type :
Electronic Resource
Accession number :
edsoai.on1438496744
Document Type :
Electronic Resource