FedBRB: An Effective Solution to the Small-to-Large Scenario in Device-Heterogeneity Federated Learning

arXiv:2402.17202v1 Announce Type: new
Abstract: Recently, the success of large models has demonstrated the importance of scaling up model size. This has spurred interest in exploring collaborative training of large-scale models from federated learning perspective. Due to computational constraints, many institutions struggle to train a large-scale model locally. Thus, training a larger global model using only smaller local models has become an important scenario (i.e., the \textbf{small-to-large scenario}). Although recent device-heterogeneity federated learning approaches have started to explore this area, …

abstract arxiv collaborative computational constraints cs.lg federated learning importance large models large-scale models perspective scale scaling scaling up small solution struggle success train training type