XGNN: Towards Model-Level Explanations of Graph Neural Networks

by   Hao Yuan, et al.

Graphs neural networks (GNNs) learn node features by aggregating and combining neighbor information, which have achieved promising performance on many graph tasks. However, GNNs are mostly treated as black-boxes and lack human intelligible explanations. Thus, they cannot be fully trusted and used in certain application domains if GNN models cannot be explained. In this work, we propose a novel approach, known as XGNN, to interpret GNNs at the model-level. Our approach can provide high-level insights and generic understanding of how GNNs work. In particular, we propose to explain GNNs by training a graph generator so that the generated graph patterns maximize a certain prediction of the model.We formulate the graph generation as a reinforcement learning task, where for each step, the graph generator predicts how to add an edge into the current graph. The graph generator is trained via a policy gradient method based on information from the trained GNNs. In addition, we incorporate several graph rules to encourage the generated graphs to be valid. Experimental results on both synthetic and real-world datasets show that our proposed methods help understand and verify the trained GNNs. Furthermore, our experimental results indicate that the generated graphs can provide guidance on how to improve the trained GNNs.


page 1

page 2

page 3

page 4


Edge-Level Explanations for Graph Neural Networks by Extending Explainability Methods for Convolutional Neural Networks

Graph Neural Networks (GNNs) are deep learning models that take graph da...

AutoGraph: Automated Graph Neural Network

Graphs play an important role in many applications. Recently, Graph Neur...

XInsight: Revealing Model Insights for GNNs with Flow-based Explanations

Progress in graph neural networks has grown rapidly in recent years, wit...

PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks

In Graph Neural Networks (GNNs), the graph structure is incorporated int...

Graph Condensation via Receptive Field Distribution Matching

Graph neural networks (GNNs) enable the analysis of graphs using deep le...

Restructuring Graph for Higher Homophily via Learnable Spectral Clustering

While a growing body of literature has been studying new Graph Neural Ne...

Introducing Expertise Logic into Graph Representation Learning from A Causal Perspective

Benefiting from the injection of human prior knowledge, graphs, as deriv...

Please sign up or login with your details

Forgot password? Click here to reset