Learning Multi-Scale Hypergraph for High-Order Brain Connectivity Analysis

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 interaction through continuous hyper-edge 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 with neurodegenerative disorders.

Brain disorders such as Alzheimer’s and Parkinson’s disease affect many regions of the brain at the same time. However, many existing AI methods analyze brain networks mainly by looking at connections between pairs of regions, which can miss broader patterns involving multiple regions. We developed MuHL, a new method that learns how groups of brain regions interact at different levels of detail. Instead of using fixed assumptions about which regions should be grouped together, MuHL learns these relationships directly from brain imaging data. We tested the method on public datasets for Alzheimer’s and Parkinson’s disease, and it improved disease-stage classification compared with existing graph and hypergraph models. MuHL also highlighted brain regions and region groups that are known to be related to disease progression. This may help researchers better understand how neurodegenerative diseases affect brain networks, while supporting more interpretable AI tools for brain imaging analysis.