# CoHyFuse: Condition-wise Hypergraph Fusion with Global Connectome in Task-fMRI

arXiv: https://arxiv.org/abs/2610.05913 · HTML: https://mlsanity.com/paper/2610.05913/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 24 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Hypergraph Neural Networks](https://mlsanity.com/paper/1809.09401/) (2018)
- [HNHN: Hypergraph Networks with Hyperedge Neurons](https://mlsanity.com/paper/2006.12278/) (2020)
- [Equivariant Hypergraph Diffusion Neural Operators](https://mlsanity.com/paper/2207.06680/) (2022)
- [Long-range Brain Graph Transformer](https://mlsanity.com/paper/2501.01100/) (2025)
- [STNAGNN: Data-driven Spatio-temporal Brain Connectivity beyond FC](https://mlsanity.com/paper/2406.12065/) (2024)
- [MHSA: A Multi-scale Hypergraph Network for Mild Cognitive Impairment Detection via Synchronous and Attentive Fusion](https://mlsanity.com/paper/2412.12149/) (2024)
- [Towards Zero-Shot Task-Generalizable Learning on fMRI](https://mlsanity.com/paper/2502.10662/) (2025)

## Abstract (arXiv)

Task-fMRI connectomes reveal state-dependent neural reconfigurations, yet conventional methods marginalize these signals by aggregating distinct conditions into static pairwise graphs, thereby obscuring condition-specific multi-ROI organization. We introduce CoHyFuse, a condition-aware ROI-centered hypergraph framework that constructs a task-state-specific incidence matrix from condition-wise functional connectivity (FC)-profile embeddings, allowing the same ROI to form different multi-ROI hyperedges across task phases. Condition-specific neighborhood sizes Kq further adapt the hyperedge scale to each task state, and the resulting condition embeddings are fused with a complementary whole-session FC branch for prediction. In the AABC cohort (N=1,074), CoHyFuse achieved the best mean out-of-fold predictive performance among evaluated baselines on FACENAME Fluid Cognition Composite (FCC) prediction (7.83±0.10 MAE, 0.439±0.026 (R2)) and VISMOTOR age prediction (7.52±0.37 MAE, 0.592±0.022 (R2)). In an auxiliary CMI-HBN attention-deficit/hyperactivity disorder (ADHD) classification benchmark (N=223), CoHyFuse obtained 72.0±2.1% macro-AUC and 74.2±2.9% accuracy. Ablation studies support the contributions of condition-wise incidence construction and dual-view fusion, suggesting that state-resolved ROI-set structure provides complementary predictive information beyond whole-session FC alone. Occlusion analysis identifies the Distraction condition as the primary driver of model prediction, pointing toward the Salience/Ventral Attention Network (SAN)--FrontoParietal Network (FPN) and within-SAN hyperedge-defined ROI-set motifs as candidate model-relevant patterns. This framework provides an interpretable, state-resolved view of the connectome for downstream cohort analysis.