ARIA: On the Interaction Between Architectures, Initialization and Aggregation Methods for Federated Visual Classification

arXiv:2311.14625v2 Announce Type: replace
Abstract: Federated Learning (FL) is a collaborative training paradigm that allows for privacy-preserving learning of cross-institutional models by eliminating the exchange of sensitive data and instead relying on the exchange of model parameters between the clients and a server. Despite individual studies on how client models are aggregated, and, more recently, on the benefits of ImageNet pre-training, there is a lack of understanding of the effect the architecture chosen for the federation has, and of how …

abstract aggregation architectures aria arxiv classification collaborative cs.ai cs.cv cs.dc data federated learning paradigm parameters privacy server studies the exchange training type visual