Reference : Efficient Federated Learning Algorithm for Resource Allocation in Wireless IoT Networks |
Scientific journals : Article | |||
Engineering, computing & technology : Electrical & electronics engineering | |||
http://hdl.handle.net/10993/44598 | |||
Efficient Federated Learning Algorithm for Resource Allocation in Wireless IoT Networks | |
English | |
Nguyen, van Dinh ![]() | |
Sharma, Shree Krishna ![]() | |
Vu, Thang Xuan ![]() | |
Chatzinotas, Symeon ![]() | |
Ottersten, Björn ![]() | |
In press | |
IEEE Internet of Things Journal | |
Institute of Electrical and Electronics Engineers | |
Yes | |
International | |
2327-4662 | |
[en] Energy-efficiency ; IoT ; federated learning | |
[en] Federated learning (FL) allows multiple edge computing nodes to jointly build a shared learning model without having to transfer their raw data to a centralized server, thus reducing communication overhead. However, FL still faces a number of challenges such as non-iid distributed data and heterogeneity of user equipments (UEs). Enabling a large number of
UEs to join the training process in every round raises a potential issue of the heavy global communication burden. To address these issues, we generalize the current state-of-the-art Federated Averaging (FedAvg) by adding a weight-based proximal term to the local loss function. The proposed FL algorithm runs stochastic gradient descent in parallel on a sampled subset of the total UEs with replacement during each global round. We provide a convergence upper bound characterizing the trade-off between convergence rate and global rounds, showing that a small number of active UEs per round still guarantees convergence. Next, we employ the proposed FL algorithm in wireless Internet-of-Things (IoT) networks to minimize either total energy consumption or completion time of FL, where a simple yet efficient path-following algorithm is developed for its solutions. Finally, numerical results on unbalanced datasets are provided to demonstrate the performance improvement and robustness on the convergence rate of the proposed FL algorithm over FedAvg. They also reveal that the proposed algorithm requires much less training time and energy consumption than the FL algorithm with full user participation. These observations advocate the proposed FL algorithm for a paradigm shift in bandwidth- constrained learning wireless IoT networks. | |
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SIGCOM | |
European Research Council | |
the ERC project AGNOSTIC | |
http://hdl.handle.net/10993/44598 | |
10.1109/JIOT.2020.3022534 | |
H2020 ; 742648 - AGNOSTIC - Actively Enhanced Cognition based Framework for Design of Complex Systems |
File(s) associated to this reference | ||||||||||||||
Fulltext file(s):
| ||||||||||||||
All documents in ORBilu are protected by a user license.