Signed Higher-Order Interactions for Brain Disorder Diagnosis via Multi-Channel Transformers

2025-07-27

AI Summary

Most existing graph neural networks model only pairwise or ternary relationships, neglecting signed higher-order interactions and thus failing to capture the complexity of coordinated brain communication. To address this, we propose the first framework integrating signed simplicial complexes with dual-filter persistent homology: it quantifies co-fluctuations via time-derivative products, constructs signed weighted higher-order topological structures, extracts multi-scale homological features, and employs a multi-channel brain Transformer for spatiotemporal joint representation learning. Our method overcomes the limitations of conventional models—namely, their restriction to low-order, unsigned interactions—achieving significant improvements in diagnostic accuracy on Alzheimer’s disease, Parkinson’s disease, and autism spectrum disorder datasets. Crucially, the identified critical brain regions and higher-order coordination patterns align with established neuroscientific findings, demonstrating both high predictive performance and biological interpretability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Humans and AI: Brain-Sensing and Analysis
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Accurately characterizing higher-order interactions of brain regions and extracting interpretable organizational patterns from Functional Magnetic Resonance Imaging data is crucial for brain disease diagnosis. Current graph-based deep learning models primarily focus on pairwise or triadic patterns while neglecting signed higher-order interactions, limiting comprehensive understanding of brain-wide communication. We propose HOI-Brain, a novel computational framework leveraging signed higher-order interactions and organizational patterns in fMRI data for brain disease diagnosis. First, we introduce a co-fluctuation measure based on Multiplication of Temporal Derivatives to detect higher-order interactions with temporal resolution. We then distinguish positive and negative synergistic interactions, encoding them in signed weighted simplicial complexes to reveal brain communication insights. Using Persistent Homology theory, we apply two filtration processes to these complexes to extract signed higher-dimensional neural organizations spatiotemporally. Finally, we propose a multi-channel brain Transformer to integrate heterogeneous topological features. Experiments on Alzheimer' s disease, Parkinson' s syndrome, and autism spectrum disorder datasets demonstrate our framework' s superiority, effectiveness, and interpretability. The identified key brain regions and higher-order patterns align with neuroscience literature, providing meaningful biological insights.

Problem

• Characterizing signed higher-order brain interactions from fMRI data
• Overcoming limitations of current graph-based models in brain disease diagnosis
• Integrating heterogeneous topological features for interpretable disease patterns

Innovation

• Signed higher-order interactions via simplicial complexes
• Multi-channel Transformer for topological integration
• Persistent Homology for spatiotemporal neural patterns