Fast Whole-Brain, Geometry-Aware Functional Alignment for Cross-Subject Decoding
Pierre-Louis Barbarant, Florent Meyniel, Bertrand Thirion
q-bio.NC, cs.LG, stat.ML
Submitted: 2026-07-12
Journal ref: Proceedings of the 9th Conference on Cognitive Computational Neuroscience, New York, NY, USA, 2026
DOI: 10.32470/gn6tuko
Code: https://github.com/nmwsharp/robust-laplacians-py
License: http://creativecommons.org/licenses/by/4.0/
The gist: Decoding brain activity is useful for characterizing brain processes and understanding the functional architecture underlying cognition.
Terminology
Abstract
Decoding brain activity is useful for characterizing brain processes and understanding the functional architecture underlying cognition. However, the inter-individual variability in brain response patterns limits the development of decoders that generalize across individuals. A solution to this challenge is functional alignment: aligning functional data across individuals before training population-level decoders. The core issue is to strike the balance between aligning functional features and preserving the anatomical structure, while maintaining computational efficiency. We introduce a new functional alignment method for fMRI, SpectralOT, that embeds cortical geometry into Laplace-Beltrami eigenmodes along functional data to regularize the alignment.
Sources
- Progressive Entropic Optimal Transport Solvers
- A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimuli
- CNeuroMod-THINGS, a densely-sampled fMRI dataset for visual neuroscience
- Aligning brain functions boosts the decoding of visual semantics in novel subjects
Related papers
- BrainWave: A Brain Signal Foundation Model for Clinical Applications
- Toward Robust, Reproducible, and Widely Accessible Intracranial Speech Brain-Computer Interfaces: A Comprehensive Narrative Review of Neural Mechanisms, Hardware, Algorithms, Evaluation, Clinical Pathways and Future Directions
- A time-causal and time-recursive scale-covariant scale-space representation of temporal signals and past time
- DRIADA: an open-source Python toolkit for linking single-neuron selectivity and population activity to behavior
- Disentanglement with Biological Constraints: A Theory of Functional Cell Types
- CytoNet: A Foundation Model for the Human Cerebral Cortex at Cellular Resolution