Learning Multi-Scale Hypergraph for High-Order Brain Connectivity Analysis
2026-06-02 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors developed a new method called MuHL to better understand complex relationships between different brain regions, which is important for detecting diseases like Alzheimer's and Parkinson's early. Unlike older methods that only look at direct pairs of brain regions, their method looks at groups of regions interacting together at different levels. They tested MuHL on brain data and found it improved disease classification and helped identify important brain areas linked to disease progression. This approach offers a more flexible way to study brain networks in neurodegenerative diseases.
brain networksgraph-based modelshypergraphhigher-order interactionsmulti-resolution analysishyperedgesnode featuresneurodegenerative diseasesAlzheimer's DiseaseParkinson's Disease
Authors
Jaeyoon Sim, Soojin Hwang, Seunghun Baek, Guorong Wu, Won Hwa Kim
Abstract
Understanding complex interactions between brain regions is critical for early neurodegenerative disease classification such as Alzheimer's Disease (AD) and Parkinson's Disease (PD). While graph-based models are widely used to analyze brain networks, most existing approaches primarily focus on pairwise interactions between directly connected nodes, limiting their ability to capture higher-order dependencies across multiple regions. Although hypergraph-based methods have been proposed to model higher-order relations, many rely on predefined hyperedges or restrict learning to hyperedge weights, reducing flexibility and limiting their capacity to capture multi-resolution structural patterns. In this regard, we introduce an adaptive multi-scale hyperedge learning framework, i.e., MuHL, which constructs hierarchical node features and dynamically learns high-order interactions through continuous hyperedge construction over multi-resolution graph signals. Extensive experiments on multiple brain network benchmarks demonstrate that MuHL consistently improves disease classification performance across different stages, and further identifies key regions of interest (ROIs) and their group-wise interactions from the learned hyperedges that are associated with disease progression, highlighting its potential as a powerful tool for brain network analysis in neurodegenerative disorders.