On Explainability of Graph Neural Networks via Subgraph Explorations

02/09/2021
by   Hao Yuan, et al.
27

We consider the problem of explaining the predictions of graph neural networks (GNNs), which otherwise are considered as black boxes. Existing methods invariably focus on explaining the importance of graph nodes or edges but ignore the substructures of graphs, which are more intuitive and human-intelligible. In this work, we propose a novel method, known as SubgraphX, to explain GNNs by identifying important subgraphs. Given a trained GNN model and an input graph, our SubgraphX explains its predictions by efficiently exploring different subgraphs with Monte Carlo tree search. To make the tree search more effective, we propose to use Shapley values as a measure of subgraph importance, which can also capture the interactions among different subgraphs. To expedite computations, we propose efficient approximation schemes to compute Shapley values for graph data. Our work represents the first attempt to explain GNNs via identifying subgraphs explicitly. Experimental results show that our SubgraphX achieves significantly improved explanations, while keeping computations at a reasonable level.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/01/2022

MotifExplainer: a Motif-based Graph Neural Network Explainer

We consider the explanation problem of Graph Neural Networks (GNNs). Mos...
research
09/16/2022

Explainability in subgraphs-enhanced Graph Neural Networks

Recently, subgraphs-enhanced Graph Neural Networks (SGNNs) have been int...
research
05/05/2022

SUGER: A Subgraph-based Graph Convolutional Network Method for Bundle Recommendation

Bundle recommendation is an emerging research direction in the recommend...
research
09/28/2022

Learning to Explain Graph Neural Networks

Graph Neural Networks (GNNs) are a popular class of machine learning mod...
research
06/11/2022

Soft-mask: Adaptive Substructure Extractions for Graph Neural Networks

For learning graph representations, not all detailed structures within a...
research
01/21/2022

Deconfounding to Explanation Evaluation in Graph Neural Networks

Explainability of graph neural networks (GNNs) aims to answer “Why the G...
research
07/14/2022

Subgraph Frequency Distribution Estimation using Graph Neural Networks

Small subgraphs (graphlets) are important features to describe fundament...

Please sign up or login with your details

Forgot password? Click here to reset