.png){kind=icon}
返回
GQFedWAvg: Optimization-Based Quantized Federated Learning in General Edge Computing Systems
.png){kind=icon}
OA
AI
DOI：10.1109/TWC.2023.3335302.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The optimal implementation of federated learning (FL) in practical edge computing systems has been an outstanding problem. In this paper, we propose an optimization-based quantized FL algorithm, which can appropriately fit a general edge computing system with uniform or nonuniform computing and communication resources at the workers. Specifically, we first present a new random quantization scheme and analyze its properties. Then, we propose a general quantized FL algorithm, namely GQFedWAvg. Specifically, GQFedWAvg applies the proposed quantization scheme to quantize wisely chosen model update-related vectors and adopts a generalized mini-batch stochastic gradient descent (SGD) method with the weighted average local model updates in global model aggregation. Besides, GQFedWAvg has several adjustable algorithm parameters to flexibly adapt to the computing and communication resources at the server and workers. We also analyze the convergence of GQFedWAvg. Next, we optimize the algorithm parameters of GQFedWAvg to minimize the convergence error under the time and energy constraints. We successfully tackle the challenging non-convex problem using general inner approximation (GIA) and multiple delicate tricks. Finally, we interpret GQFedWAvg's function principle and show its considerable gains over existing FL algorithms using numerical results.
Keyword:
Quantization (signal)
Servers
Convergence
Computational modeling
Edge computing
Costs
Wireless communication
Federated learning
stochastic gradient descent
quantization
convergence analysis
optimization
期刊
IF:
10.7
论文数:
1.3W
被引数:
5.3W
机构
引用论文
分享收藏Adaptive Control of Local Updating and Model Compression for Efficient Federated Learning用于有效联邦学习的局部更新和模型压缩的自适应控制
PREAI
分享收藏Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing边缘智能: 用边缘计算铺平人工智能的最后一英里.png)
PROCEEDINGS OF THE IEEE
OAAI
PROCEEDINGS OF THE IEEEIF25.9
OAAI分享收藏Ecological Principles for the Establishment and Management of National Parks and Equivalent ReservesOAAI
OAAI分享收藏Sorption of 17α-ethinyl estradiol, bisphenol A and phenanthrene to different size fractions of soil and sedimentChemosphere
ChemosphereIF0
PREAI
分享收藏
查看更多内容