Pith. sign in

REVIEW 4 cited by

GNNExplainer: Generating Explanations for Graph Neural Networks

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 1903.03894 v4 pith:66TKF2MC submitted 2019-03-10 cs.LG stat.ML

classification cs.LGstat.ML
keywords gnnexplainergraphgnnsexplanationsinformationneuralnodestructure
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Graph Neural Networks (GNNs) are a powerful tool for machine learning on graphs.GNNs combine node feature information with the graph structure by recursively passing neural messages along edges of the input graph. However, incorporating both graph structure and feature information leads to complex models, and explaining predictions made by GNNs remains unsolved. Here we propose GNNExplainer, the first general, model-agnostic approach for providing interpretable explanations for predictions of any GNN-based model on any graph-based machine learning task. Given an instance, GNNExplainer identifies a compact subgraph structure and a small subset of node features that have a crucial role in GNN's prediction. Further, GNNExplainer can generate consistent and concise explanations for an entire class of instances. We formulate GNNExplainer as an optimization task that maximizes the mutual information between a GNN's prediction and distribution of possible subgraph structures. Experiments on synthetic and real-world graphs show that our approach can identify important graph structures as well as node features, and outperforms baselines by 17.1% on average. GNNExplainer provides a variety of benefits, from the ability to visualize semantically relevant structures to interpretability, to giving insights into errors of faulty GNNs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Structure-Aware Compound-Protein Affinity Prediction via Graph Neural Networks with Group Lasso Regularization

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Adding common-plus-uncommon substructure masks and group lasso or sparse group lasso losses to activity-cliff GNNs improves per-target pIC50 prediction and attribution consistency on six tyrosine kinases.

  2. Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networks

    cs.LG 2025-05 reject novelty 6.0 of 10

    ConfExplainer adds a confidence score to GNN edge explanations via a graph information bottleneck variant, claiming better explanation accuracy and reliability.

  3. Atherosclerosis through Hierarchical Explainable Neural Network Analysis

    cs.LG 2025-07 reject novelty 5.0 of 10

    A hierarchical graph network that fuses patient-specific PPI graphs with a clinical patient-similarity graph improves atherosclerosis subtype classification and suggests two molecular clusters per imaging subtype, but...

  4. Graph Neural Networks in Multi-Omics Cancer Research: A Structured Survey

    cs.LG 2025-06 conditional novelty 3.0 of 10

    A structured survey of GNN-based multi-omics cancer studies that categorizes 75 papers by task, architecture, and omics type, but contains duplicated text, inconsistent counts, and an unsupported 'first survey' claim.

Pith tools