aiqbench analysis
This paper applies graph contrastive learning to resting-state fMRI for diagnosing brain disorders. Its main technical contributions are a dynamic augmentation module that refines graph topology across training epochs and a multi-view contrastive objective, with a theoretical lower bound offered for the loss. Readers should note that the reported gains rest on two public datasets (1,236 subjects total), so generalization to other scanners, populations, and clinical settings remains to be shown.
MCDA: Multi-View Graph Contrastive Learning with Dynamic Topology Augmentation for Functional MRI Analysis
arXiv:2610.26322v1 Announce Type: cross Abstract: Resting-state fMRI (rs-fMRI) is a vital non-invasive tool for diagnosing brain disorders and uncovering pathological mechanisms. However, existing graph contrastive learning (GCL) methods often underexploit augmentation histories across training epochs and the relationships among different augmented views. In this paper, we introduce a topology-guided Multi-view graph Contrastive learning framework with Dynamic graph topology Augmentation (MCDA) for fMRI analysis. Unlike traditional GCL that uses fixed noise or edge-dropping, MCDA employs a Dynamic Augmentation Update (DAU) module that iteratively refines the augmented topology. Specifically, we incorporate self-aware and cross-sample augmentation strategies to simultaneously capture individual-specific functional signatures and inter-subject heterogeneity. We then design a topology-guided multi-view graph contrastive learning scheme that explores interrelationships not only between the original network and its augmented views, but also across different augmented views to maximize structural information preservation. We characterize the score-level optimization directions and establish a lower bound for the contrastive objective. The framework combines classification and contrastive losses for brain disorder diagnosis and examines discriminative functional connectivity patterns as potential biomarkers. Experiments on two public rs-fMRI datasets comprising 1,236 subjects demonstrate that MCDA outperforms the state-of-the-art methods. The code has been made publicly available at: \url{https://github.com/goodcodingagoodboy/MCDA}.
Abstract:Resting-state fMRI (rs-fMRI) is a vital non-invasive tool for diagnosing brain disorders and uncovering pathological mechanisms. However, existing graph contrastive learning (GCL) methods often underexploit augmentation histories across training epochs and the relationships among different augmented views. In this paper, we introduce a topology-guided Multi-view graph Contrastive learning framework with Dynamic graph topology Augmentation (MCDA) for fMRI analysis. Unlike traditional GCL that uses fixed noise or edge-dropping, MCDA employs a Dynamic Augmentation Update (DAU) module that iteratively refines the augmented topology. Specifically, we incorporate self-aware and cross-sample augmentation strategies to simultaneously capture individual-specific functional signatures and inter-subject heterogeneity. We then design a topology-guided multi-view graph contrastive learning scheme that explores interrelationships not only between the original network and its augmented views, but also across different augmented views to maximize structural information preservation. We characterize the score-level optimization directions and establish a lower bound for the contrastive objective. The framework combines classification and contrastive losses for brain disorder diagnosis and examines discriminative functional connectivity patterns as potential biomarkers. Experiments on two public rs-fMRI datasets comprising 1,236 subjects demonstrate that MCDA outperforms the state-of-the-art methods. The code has been made publicly available at: \url{this https URL}.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2610.26322 [cs.CV]
(or arXiv:2610.26322v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.26322 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 292 words
Related coverage
Contrast-Informed Augmentation and Domain-Adversarial Training for Adult-to-Neonatal MR Reconstruction Generalization
arXiv · Jun 12, 2026
DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models
arXiv · Sep 29, 2026
A Comparison of Data Augmentation Methods for Training Deep Neural Networks on Synthetic Aperture Sonar
arXiv · Jul 28, 2026
SAFECAST: Robust Failure Detection for VLA Policies with Contrast-Set Training and Calibration
arXiv · Aug 6, 2026