Federated Multi-Task Learning on Non-IID Data Silos: An Experimental Study

arXiv:2402.12876v1 Announce Type: new
Abstract: The innovative Federated Multi-Task Learning (FMTL) approach consolidates the benefits of Federated Learning (FL) and Multi-Task Learning (MTL), enabling collaborative model training on multi-task learning datasets. However, a comprehensive evaluation method, integrating the unique features of both FL and MTL, is currently absent in the field. This paper fills this void by introducing a novel framework, FMTL-Bench, for systematic evaluation of the FMTL paradigm. This benchmark covers various aspects at the data, model, and optimization …

abstract arxiv benefits collaborative cs.cr cs.dc cs.lg data datasets data silos enabling evaluation experimental features federated learning multi-task learning study training type