Generative Explanations for Graph Neural Network: Methods and Evaluations
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:WBZZ2N63record.jsonopen to challenge →
read the original 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.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.