BrainRiem: Riemannian Prototype Learning for Source-Free Cross-Site Brain Network Diagnosis

We propose BrainRiem, a source-free domain adaptation framework that learns compact Riemannian brain prototypes via manifold-aware bi-level optimization for privacy-preserving cross-site brain network diagnosis under scanner and demographic shifts.

Authors: Kunyu Zhang*, Tianxiang Xu*
* Equal contribution

Links: [Paper]