Extract and Refine Brain Subgraph for Disorder Analysis via Cross-Domain Learning
- 27 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 12 (4) , 1137-1150
Abstract
Brain graphs (brain connectivity networks) play an important role in modeling the complex structure of the human brain. Furthermore, brain graph learning based on graph neural networks (GNNs) has recently attracted growing interest. Although existing methods have made great progress in brain disorder prediction and pathogenic analysis, there are two key problems: (1) They rarely utilize the pathogenic reason of brain disorders, that is, salient brain regions always lead to abnormal connections between brain regions, to extract critical brain graph information for disorder analysis; (2) Since most of the available brain graph data is limited, how can we improve the performance of brain graph learning models on insufficient training data? Thus, in this paper, we learn brain graph representations for disorder prediction and analyze disorder-specific brain regions and connections from the subgraph perspective. Besides, we introduce the cross-domain brain graph learning framework to alleviate the problem of poor model performance on limited data. To consider the pathogenic reason by brain subgraphs, we first propose the node entropy of brain graphs based on brain graph properties to extract important nodes. We then introduce subgraph information bottleneck to refine the critical subgraph from the rough subgraph generated by these important nodes, recognizing important connections related to disorders. To achieve a better model performance on limited data, we design a cross-domain brain graph learning framework to improve the subgraph extraction model by the meta-learning method. The subgraph extraction model is pre-trained on a large source training dataset and then quickly adapted to target task dataset. Besides, a simple yet effective feature alignment module is applied to mitigate the negative transfer problem for cross-domain datasets. Extensive experimental results, including disorder prediction and pathogenic analysis on real-world neuroimaging data, demonstrate the effectiveness of our method.Keywords
Funding Information
- Australian Research Council Projects (DP230100899)
- Australian Research Council Projects (LP210301259)
- Australian Research Council Projects (DP260100944)
- Australian Research Council Projects (FT250100159)
This publication has 49 references indexed in Scilit:
- Graph explicit pooling for graph-level representation learningNeural Networks, 2024
- ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learning2023
- Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis2022
- Deep reinforcement learning guided graph neural networks for brain network analysisNeural Networks, 2022
- BrainGNN: Interpretable Brain Graph Neural Network for fMRI AnalysisMedical Image Analysis, 2021
- Hi-GCN: A hierarchical graph convolution network for graph embedding learning of brain network and brain disorders predictionComputers in Biology and Medicine, 2020
- Graph neural networks: A review of methods and applicationsAI Open, 2020
- Semi-supervised Tensor Factorization for Brain Network Analysis2016
- Complex network measures of brain connectivity: Uses and interpretationsNeuroImage, 2010
- Automated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject BrainNeuroImage, 2002