DeepAI AI Chat
Log In Sign Up

Generative Causal Explanations for Graph Neural Networks

by   Wanyu Lin, et al.

This paper presents Gem, a model-agnostic approach for providing interpretable explanations for any GNNs on various graph learning tasks. Specifically, we formulate the problem of providing explanations for the decisions of GNNs as a causal learning task. Then we train a causal explanation model equipped with a loss function based on Granger causality. Different from existing explainers for GNNs, Gem explains GNNs on graph-structured data from a causal perspective. It has better generalization ability as it has no requirements on the internal structure of the GNNs or prior knowledge on the graph learning tasks. In addition, Gem, once trained, can be used to explain the target GNN very quickly. Our theoretical analysis shows that several recent explainers fall into a unified framework of additive feature attribution methods. Experimental results on synthetic and real-world datasets show that Gem achieves a relative increase of the explanation accuracy by up to 30% and speeds up the explanation process by up to 110× as compared to its state-of-the-art alternatives.


page 1

page 2

page 3

page 4


OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks

This paper proposes a new eXplanation framework, called OrphicX, for gen...

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

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

Faithful Explanations for Deep Graph Models

This paper studies faithful explanations for Graph Neural Networks (GNNs...

On Consistency in Graph Neural Network Interpretation

Uncovering rationales behind predictions of graph neural networks (GNNs)...

Task-Agnostic Graph Explanations

Graph Neural Networks (GNNs) have emerged as powerful tools to encode gr...

A Meta-Learning Approach for Training Explainable Graph Neural Networks

In this paper, we investigate the degree of explainability of graph neur...

Reinforced Causal Explainer for Graph Neural Networks

Explainability is crucial for probing graph neural networks (GNNs), answ...