Metadata-Driven Federated Learning of Connectional Brain Templates in Non-IID Multi-Domain Scenarios

arXiv:2403.09139v1 Announce Type: new
Abstract: A connectional brain template (CBT) is a holistic representation of a population of multi-view brain connectivity graphs, encoding shared patterns and normalizing typical variations across individuals. The federation of CBT learning allows for an inclusive estimation of the representative center of multi-domain brain connectivity datasets in a fully data-preserving manner. However, existing methods overlook the non-independent and identically distributed (non-IDD) issue stemming from multidomain brain connectivity heterogeneity, in which data domains are drawn from different …

abstract arxiv brain center connectivity cs.cv domain encoding federated learning federation graphs metadata patterns population representation template type view