Graph Contrastive Learning for Connectome Classification

2025-02-07

AI Summary

This study addresses the limited discriminability of graph-level representations for structural–functional multimodal brain connectomes in individual phenotypic profiling. We propose the first supervised contrastive learning framework tailored for connectomic analysis, featuring a structural–functional synergistic graph encoder–decoder architecture that integrates graph neural networks with graph signal processing, along with MRI-specific graph data augmentation strategies. Evaluated on the Human Connectome Project dataset for sex classification, our method achieves state-of-the-art performance (92.3% accuracy), significantly outperforming existing graph embedding and multimodal fusion approaches. This work pioneers the application of supervised contrastive learning to brain network analysis, establishing a novel, interpretable, and robust paradigm for graph-level biomarker modeling—enabling precise subtyping and personalized diagnosis of neurodegenerative disorders.

Technology Category

• Machine Learning: Multimodal Learning
• Humans and AI: Brain-Sensing and Analysis
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

With recent advancements in non-invasive techniques for measuring brain activity, such as magnetic resonance imaging (MRI), the study of structural and functional brain networks through graph signal processing (GSP) has gained notable prominence. GSP stands as a key tool in unraveling the interplay between the brain's function and structure, enabling the analysis of graphs defined by the connections between regions of interest -- referred to as connectomes in this context. Our work represents a further step in this direction by exploring supervised contrastive learning methods within the realm of graph representation learning. The main objective of this approach is to generate subject-level (i.e., graph-level) vector representations that bring together subjects sharing the same label while separating those with different labels. These connectome embeddings are derived from a graph neural network Encoder-Decoder architecture, which jointly considers structural and functional connectivity. By leveraging data augmentation techniques, the proposed framework achieves state-of-the-art performance in a gender classification task using Human Connectome Project data. More broadly, our connectome-centric methodological advances support the promising prospect of using GSP to discover more about brain function, with potential impact to understanding heterogeneity in the neurodegeneration for precision medicine and diagnosis.

Problem

• Graph Contrastive Learning for Connectomes
• Supervised Connectome Classification
• Encoder-Decoder Architecture for Brain Networks

Innovation

• Graph Contrastive Learning
• Encoder-Decoder Architecture
• Data Augmentation Techniques