Federated multi-task learning with cross-device heterogeneous task subsets

Zewei Xin

doi:10.1016/j.jpdc.2025.105155

Federated multi-task learning with cross-device heterogeneous task subsets

2025-07-25

0

PRE

AI

DOI：10.1016/j.jpdc.2025.105155

Original

Original request for help

Save

Abstract

En 中文

• We propose cross-device task heterogeneity, a collaborative scenario for federated clients with heterogeneous task sets. • We propose FedPMT, enabling clients with diverse task sets to collaboratively train cloud models, with proven convergence. • We use different model architectures locally and in the cloud for their tasks, enabling collaboration through alignment. • We propose task attenuation factors to promote task collaboration, enabling cloud models to converge to shared optima. • Extensive experiments verify the effectiveness of our method in various heterogeneous task set scenarios.

Keywords:

cross-device task heterogeneity

federated learning

model alignment

task attenuation factors

collaborative training

Federated multi-task learning with cross-device heterogeneous task subsets

Abstract

Journal

Organization