Abstract
Forecasting time-varying functional connectivity from electroencephalography (EEG) requires modeling both history-dependent trends and structured variability across channels. Conditional flow matching provides a framework for distributional forecasting, yet it remains unclear whether graph-informed source distributions offer practical advantages over isotropic noise and strong deterministic predictors. We introduce a graph-structured residual flow framework that separates conditional mean prediction from stochastic residual transport. A history-only predictor estimates the future connectivity graph, while a graph Gaussian source encodes dependencies derived from past connectivity through a Laplacian-based covariance. A conditional velocity field transports source samples to future graph residuals, with transport time explicitly distinguished from physical EEG time. Our study identifies the conditions and controls needed to distinguish useful residual transport from improvements attributable to deterministic prediction, learned representations, and sampling effects.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Jia, H., Chen, Z., Pradeepkumar, J., Cao, X., Matsubara, Y., Sakurai, Y., & Matsubara, T. (2026). GRFBrain: Graph-Structured Rectified Flows for EEG Dynamic Modeling. https://omanscience.com/en/articles/grfbrain-graph-structured-rectified-flows-for-eeg-dynamic-modeling
MLA 9
Jia, Haohui, et al. "GRFBrain: Graph-Structured Rectified Flows for EEG Dynamic Modeling." https://omanscience.com/en/articles/grfbrain-graph-structured-rectified-flows-for-eeg-dynamic-modeling.
Chicago (author–date)
Jia, Haohui, Zheng Chen, Jathurshan Pradeepkumar, Xu Cao, Yasuko Matsubara, Yasushi Sakurai, and Takashi Matsubara. 2026. "GRFBrain: Graph-Structured Rectified Flows for EEG Dynamic Modeling." https://omanscience.com/en/articles/grfbrain-graph-structured-rectified-flows-for-eeg-dynamic-modeling.
Harvard
Jia, H., Chen, Z., Pradeepkumar, J., Cao, X., Matsubara, Y., Sakurai, Y. and Matsubara, T. (2026) 'GRFBrain: Graph-Structured Rectified Flows for EEG Dynamic Modeling', Available at: https://omanscience.com/en/articles/grfbrain-graph-structured-rectified-flows-for-eeg-dynamic-modeling.
Vancouver
Jia H, Chen Z, Pradeepkumar J, Cao X, Matsubara Y, Sakurai Y, et al. GRFBrain: Graph-Structured Rectified Flows for EEG Dynamic Modeling. https://omanscience.com/en/articles/grfbrain-graph-structured-rectified-flows-for-eeg-dynamic-modeling
IEEE
H. Jia, Z. Chen, J. Pradeepkumar, X. Cao, Y. Matsubara, Y. Sakurai, and T. Matsubara, "GRFBrain: Graph-Structured Rectified Flows for EEG Dynamic Modeling," https://omanscience.com/en/articles/grfbrain-graph-structured-rectified-flows-for-eeg-dynamic-modeling.