CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosis

01/04/2023
by   Kaizhong Zheng, et al.
0

There is a recent trend to leverage the power of graph neural networks (GNNs) for brain-network based psychiatric diagnosis, which,in turn, also motivates an urgent need for psychiatrists to fully understand the decision behavior of the used GNNs. However, most of the existing GNN explainers are either post-hoc in which another interpretive model needs to be created to explain a well-trained GNN, or do not consider the causal relationship between the extracted explanation and the decision, such that the explanation itself contains spurious correlations and suffers from weak faithfulness. In this work, we propose a granger causality-inspired graph neural network (CI-GNN), a built-in interpretable model that is able to identify the most influential subgraph (i.e., functional connectivity within brain regions) that is causally related to the decision (e.g., major depressive disorder patients or healthy controls), without the training of an auxillary interpretive network. CI-GNN learns disentangled subgraph-level representations α and e̱ṯa̱ that encode, respectively, the causal and noncausal aspects of original graph under a graph variational autoencoder framework, regularized by a conditional mutual information (CMI) constraint. We theoretically justify the validity of the CMI regulation in capturing the causal relationship. We also empirically evaluate the performance of CI-GNN against three baseline GNNs and four state-of-the-art GNN explainers on synthetic data and two large-scale brain disease datasets. We observe that CI-GNN achieves the best performance in a wide range of metrics and provides more reliable and concise explanations which have clinical evidence.

READ FULL TEXT

page 33

page 34

research
12/02/2021

ProtGNN: Towards Self-Explaining Graph Neural Networks

Despite the recent progress in Graph Neural Networks (GNNs), it remains ...
research
05/07/2022

BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck

Developing a new diagnostic models based on the underlying biological me...
research
09/12/2023

Explainable Graph Neural Network for Alzheimer's Disease And Related Dementias Risk Prediction

Alzheimer's disease and related dementias (ADRD) ranks as the sixth lead...
research
01/07/2023

Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment

Uncovering rationales behind predictions of graph neural networks (GNNs)...
research
01/30/2023

Causality-based CTR Prediction using Graph Neural Networks

As a prevalent problem in online advertising, CTR prediction has attract...
research
07/11/2021

BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis

Interpretable brain network models for disease prediction are of great v...
research
06/17/2021

Predicting cognitive scores with graph neural networks through sample selection learning

Analyzing the relation between intelligence and neural activity is of th...

Please sign up or login with your details

Forgot password? Click here to reset