Toward a Multi-View Brain Network Foundation Model: Cross-View Consistency Learning Across Arbitrary Atlases

TL;DR

This paper introduces MV-BrainFM, a multi-view brain network foundation model that learns atlas-independent, scalable representations by integrating anatomical priors and cross-view consistency, improving brain network analysis across diverse datasets.

Contribution

The paper presents a novel multi-view brain network foundation model that explicitly incorporates anatomical priors and cross-view consistency learning, enabling scalable and generalizable brain network representations.

Findings

Outperforms 14 existing models across 20K+ subjects

Effectively captures complementary information from multiple atlases

Maintains stable performance across unseen atlas configurations

Abstract

Brain network analysis provides an interpretable framework for characterizing brain organization and has been widely used for neurological disorder identification. Recent advances in self-supervised learning have motivated the development of brain network foundation models. However, existing approaches are often limited by atlas dependency, insufficient exploitation of multiple network views, and weak incorporation of anatomical priors. In this work, we propose MV-BrainFM, a multi-view brain network foundation model designed to learn generalizable and scalable representations from brain networks constructed with arbitrary atlases. MV-BrainFM explicitly incorporates anatomical distance information into Transformer-based modeling to guide inter-regional interactions, and introduces an unsupervised cross-view consistency learning strategy to align representations from multiple atlases of the same subject in a shared latent space. By jointly enforcing within-view robustness and cross-view alignment during pretraining, the model effectively captures complementary information across heterogeneous network views while remaining atlas-aware. In addition, MV-BrainFM adopts a unified multi-view pretraining paradigm that enables simultaneous learning from multiple datasets and atlases, significantly improving computational efficiency compared to conventional sequential training strategies. The proposed framework also demonstrates strong scalability, consistently benefiting from increasing data diversity while maintaining stable performance across unseen atlas configurations. Extensive experiments on more than 20K subjects from 17 fMRI datasets show that MV-BrainFM consistently outperforms 14 existing brain network foundation models and task-specific baselines under both single-atlas and multi-atlas settings.