Work

Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations

Year: 2026

Type: conference-paper

Abstract: Functional magnetic resonance imaging (fMRI) analysis faces significant challenges due to limited dataset sizes and domain variability between studies. Traditional self-supervised learning methods inspired by computer vision often rely on positive and negative sample pairs, which can be problematic for neuroimaging data where defining appropriate contrasts is non-trivial. We propose adapting a recently developed Hierarchical Functional Maximal Correlation Algorithm (HFMCA) to graph-structured fMRI data, providing a theoretically grounded approach that measures statistical dependence via density ratio decomposition in a reproducing kernel Hilbert space (RKHS), and applies HFMCA-based pretraining to learn robust and generalizable representations. Evaluations across five neuroimaging datasets demonstrate that our adapted method produces competitive embeddings for various classification tasks and enables effective knowledge transfer to unseen datasets. Codebase and supplementary material can be found here: https://github.com/fr30/mri-eigenencoder

Source: IEEE International Conference on Acoustics Speech and Signal Processing

DOI: 10.1109/icassp55912.2026.11460861

Authors: Jakub Frąc, Alexander Schmatz, Qiang Li, Guido Van Wingen, Shujian Yu

Institutions: Vrije Universiteit Amsterdam, Center for Translational Research in Neuroimaging and Data Science, Amsterdam University Medical Centers

Language: English

Topic: Functional Brain Connectivity Studies

Subfield: Cognitive Neuroscience

Field: Neuroscience

Domain: Life Sciences

SDG: Good health and well-being

Open Access status: green

Funder: Vrije Universiteit Amsterdam