Fair Concurrent Training of Multiple Models in Federated Learning

arXiv:2404.13841v1 Announce Type: new
Abstract: Federated learning (FL) enables collaborative learning across multiple clients. In most FL work, all clients train a single learning task. However, the recent proliferation of FL applications may increasingly require multiple FL tasks to be trained simultaneously, sharing clients' computing and communication resources, which we call Multiple-Model Federated Learning (MMFL). Current MMFL algorithms use naive average-based client-task allocation schemes that can lead to unfair performance when FL tasks have heterogeneous difficulty levels, e.g., tasks with …

abstract applications arxiv call collaborative communication computing cs.ai cs.lg fair federated learning however multiple resources tasks train training type work