BROWSE
Detail
Journal Article
DRL-empowered joint batch size and weighted aggregation adjustment mechanism for federated learning on non-IID data
- Authors
- Juneseok Bang, Sungpil Woo, Joohyung Lee
- Issue Date
- 2024-08
- Citation
- ICT EXPRESS, v.10, no.4, pp.863-870
- ISSN
- 2405-9595
- Publisher
- ELSEVIER
- Language
- English
- Type
- Journal Article
- Abstract
- To address the accuracy degradation as well as prolonged convergence time due to the inherent data heterogeneity among end-devices in federated learning (FL), we introduce the joint batch size and weighted aggregation adjustment problem, which is non-convex problem. To adjust optimal hyperparameters, we develop deep reinforcement learning (DRL) to empower a mechanism known as Batch size and Weighted aggregation Adjustment (BWA). Experimental evaluation demonstrates that BWA not only outperforms methods optimized solely from either a local training or server perspective but also achieves higher accuracy, with an increase of up to 5.53% compared to FedAvg, and additionally accelerates convergence speeds.
- KSP Keywords
- Batch size, Data heterogeneity, Deep reinforcement learning, Federated learning, Local training, Reinforcement learning(RL), Weighted aggregation, adjustment mechanism, convergence time, experimental evaluation, non-Convex Problem
This work is distributed under the term of Creative Commons License (CCL)
(CC BY NC ND)
(CC BY NC ND)
