BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis
arXiv:2107.05097
Abstract
Interpretable brain network models for disease prediction are of great value for the advancement of neuroscience. GNNs are promising to model complicated network data, but they are prone to overfitting and suffer from poor interpretability, which prevents their usage in decision-critical scenarios like healthcare. To bridge this gap, we propose BrainNNExplainer, an interpretable GNN framework for brain network analysis. It is mainly composed of two jointly learned modules: a backbone prediction model that is specifically designed for brain networks and an explanation generator that highlights disease-specific prominent brain network connections. Extensive experimental results with visualizations on two challenging disease prediction datasets demonstrate the unique interpretability and outstanding performance of BrainNNExplainer.
arXiv commentThis paper has been accepted to ICML 2021 Workshop on Interpretable Machine Learning in Healthcare
References in corpus (9)
- Fast Graph Representation Learning with PyTorch Geometric
- Spectral methods for network community detection and graph partitioning
- Parameterized Explainer for Graph Neural Network
- Invariant and Equivariant Graph Networks
- A simple yet effective baseline for non-attributed graph classification
- Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
- Boosted Sparse and Low-Rank Tensor Regression
- On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs
- Multi-View Multi-Graph Embedding for Brain Network Clustering Analysis