analiza aiqbench
MuHL introduces an adaptive multi-scale hypergraph framework that dynamically learns high-order interactions across brain regions, overcoming the limitations of traditional pairwise graph models. By constructing hierarchical features over multi-resolution signals, the method significantly improves early classification performance for neurodegenerative diseases like Alzheimer's and Parkinson's while identifying key disease-associated regions. This approach advances the state-of-the-art in graph-based medical imaging by effectively capturing complex, non-local dependencies within brain networks.
Learning Multi-Scale Hypergraph for High-Order Brain Connectivity Analysis
arXiv:2606.03310v1 Announce Type: cross 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.
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.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2606.03310 [cs.LG]
(or arXiv:2606.03310v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.03310 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 268 cuvinte
Subiecte conexe
Does preservation make sense before we know how to revive?
LessWrong · 15 iun. 2026
HyperAMS-Net: Adaptive Multi-Scale Spatial Hypergraph Network for Brain Disorder Classification
arXiv · 18 sept. 2026
Links #5: 2026/07
LessWrong · 31 iul. 2026
Presentation: Beyond Prompting: Context Engineering and Memory Management for AI Systems at Scale
InfoQ · 10 iun. 2026