PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networks

10/31/2022
by   Yong-Min Shin, et al.
0

Aside from graph neural networks (GNNs) catching significant attention as a powerful framework revolutionizing graph representation learning, there has been an increasing demand for explaining GNN models. Although various explanation methods for GNNs have been developed, most studies have focused on instance-level explanations, which produce explanations tailored to a given graph instance. In our study, we propose Prototype-bAsed GNN-Explainer (PAGE), a novel model-level GNN explanation method that explains what the underlying GNN model has learned for graph classification by discovering human-interpretable prototype graphs. Our method produces explanations for a given class, thus being capable of offering more concise and comprehensive explanations than those of instance-level explanations. First, PAGE selects embeddings of class-discriminative input graphs on the graph-level embedding space after clustering them. Then, PAGE discovers a common subgraph pattern by iteratively searching for high matching node tuples using node-level embeddings via a prototype scoring function, thereby yielding a prototype graph as our explanation. Using five graph classification datasets, we demonstrate that PAGE qualitatively and quantitatively outperforms the state-of-the-art model-level explanation method. We also carry out experimental studies systematically by showing the relationship between PAGE and instance-level explanation methods, the robustness of PAGE to input data scarce environments, and the computational efficiency of the proposed prototype scoring function in PAGE.

READ FULL TEXT

page 6

page 9

page 14

page 16

research
02/24/2023

PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction

Transparency and accountability have become major concerns for black-box...
research
10/05/2022

Towards Prototype-Based Self-Explainable Graph Neural Network

Graph Neural Networks (GNNs) have shown great ability in modeling graph-...
research
04/14/2023

KS-GNNExplainer: Global Model Interpretation Through Instance Explanations On Histopathology images

Instance-level graph neural network explainers have proven beneficial fo...
research
08/04/2022

Explaining Classifiers Trained on Raw Hierarchical Multiple-Instance Data

Learning from raw data input, thus limiting the need for feature enginee...
research
05/20/2022

Towards Explanation for Unsupervised Graph-Level Representation Learning

Due to the superior performance of Graph Neural Networks (GNNs) in vario...
research
10/26/2020

Contrastive Graph Neural Network Explanation

Graph Neural Networks achieve remarkable results on problems with struct...
research
10/20/2022

Toward Multiple Specialty Learners for Explaining GNNs via Online Knowledge Distillation

Graph Neural Networks (GNNs) have become increasingly ubiquitous in nume...

Please sign up or login with your details

Forgot password? Click here to reset