Chapter7: Interpretability in Graph Neural Networks

Ninghao Liu, Texas A&M University,
Qizhang Feng, Texas A&M University,
Xia Hu, Texas A&M University,


Interpretable machine learning, or explainable artificial intelligence, is experiencing rapid developments to tackle the opacity issue of deep learning techniques. In graph analysis, motivated by the effectiveness of deep learning, graph neural networks (GNNs) are becoming increasingly popular in modeling graph data. Recently, an increasing number of approaches have been proposed to provide explanations for GNNs or to improve GNN interpretability. In this chapter, we offer a comprehensive survey to summarize these approaches. Specifically, in the first section, we review the fundamental concepts of interpretability in deep learning. In the second section, we introduce the post-hoc explanation methods for understanding GNN predictions. In the third section, we introduce the advances of developing more interpretable models for graph data. In the fourth section, we introduce the datasets and metrics for evaluating interpretation. Finally, we point out future directions of the topic.


  • Introduction: Interpretability in Deep Models
    • Definition of Interpretability and Interpretation
    • The Value of Interpretation
    • Traditional Interpretation Methods
    • Opportunities and Challenges in GNN Interpretability
  • Explanation Methods for Graph Neural Networks
    • Background
    • Approximation-Based Explanation
    • Relevance-Propogation Based Explanation
    • Perturbation-Based Approaches
    • Generative Explanation
  • Interpretable Modeling on GNNs
    • GNN-Based Attention Models
    • Disentangled Representation Learning on Graphs
  • Evaluation of GNN Explanations
    • Benchmark Datasets
    • Evaluation Metrics
  • Future Directions


author = "Liu, Ninghao and Feng, Qizhang and Hu, Xia",
editor = "Wu, Lingfei and Cui, Peng and Pei, Jian and Zhao, Liang",
title = "Interpretability in Graph Neural Networks",
booktitle = "Graph Neural Networks: Foundations, Frontiers, and Applications",
year = "2022",
publisher = "Springer Singapore",
address = "Singapore",
pages = "121--147",

N. Liu, Q. Feng, and X. Hu, “Interpretability in graph neural networks,” in Graph Neural Networks: Foundations, Frontiers, and Applications, L. Wu, P. Cui, J. Pei, and L. Zhao, Eds. Singapore: Springer Singapore, 2022, pp. 121–147.