HFedMTL: Hierarchical Federated Multi-Task Learning

Federated learning is an effective way to enable artificial intelligence over massive distributed nodes with security and communication efficiency. Some previous works primarily focus on learning a single global model for a unique task across the network, which is less competent to handle multi-task...

Full description

Saved in:
Bibliographic Details
Published in2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) pp. 1 - 6
Main Authors Yi, Xingfu, Li, Rongpeng, Peng, Chenghui, Wu, Jianjun, Zhao, Zhifeng
Format Conference Proceeding
LanguageEnglish
Published IEEE 12.09.2022
Subjects
Artificial intelligence (AI)
Computational modeling
Costs
Federated learning
Learning systems
Mobile Edge Computing
Multi-Task Learning
Multitasking
Security
Simulation
Online AccessGet full text

Cover

More Information
Summary:Federated learning is an effective way to enable artificial intelligence over massive distributed nodes with security and communication efficiency. Some previous works primarily focus on learning a single global model for a unique task across the network, which is less competent to handle multi-task scenarios with stragglers and fault, after adopting the general gradient update methods in a federated environment. Others aim to learn a distinct model for each node, which is expensive in terms of the computation and communication cost. Using hierarchical network to reduce communication cost is becoming a new candidate. Thus, we propose a primal-and-dual method-based hierarchical federated multi-task learning system, supported with HFedMTL algorithm that allows massive nodes from distributed areas to join in the federated multi-task learning process. Empirical experiments verify the analysis and demonstrate the benefits of improving the learning performance and convergence rate.
ISSN:2166-9589
DOI:10.1109/PIMRC54779.2022.9977670