Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

GNNExplainer: Generating Explanations for Graph Neural Networks

About

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.

Rex Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, Jure Leskovec• 2019

Related benchmarks

TaskDatasetResultRank
Graph ClassificationPROTEINS
Accuracy71.9
994
Graph ClassificationMUTAG
Accuracy66.5
862
Node ClassificationCora (test)--
861
Graph ClassificationCOLLAB
Accuracy77.6
422
Graph ClassificationIMDB-M
Accuracy45
275
Graph ClassificationPTC-MR
Accuracy67.1
197
Graph ClassificationDHFR
Accuracy69.8
140
Graph ClassificationBZR
Accuracy81.1
89
Graph ClassificationCOX2
Accuracy80.7
80
Graph ClassificationIMDB-B
Mean Accuracy70.4
39
Showing 10 of 86 rows
...

Other info

Follow for update