Pith. sign in

REVIEW 1 cited by

Generative Explanations for Graph Neural Network: Methods and Evaluations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.05764 v1 pith:WBZZ2N63 submitted 2023-11-09 cs.LG

classification cs.LG
keywords explanationmethodsgenerativegnnsgraphdemonstratedifferentexplainability
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. NAEx: A Plug-and-Play Framework for Explaining Network Alignment

    cs.LG 2025-08 conditional novelty 6.0 of 10

    NAEx is a plug-and-play explainer that identifies the key subgraphs and features driving network alignment predictions, and it generalizes to new pairs without retraining.

Pith tools