.png){kind=icon}
返回
Communication Efficient Decentralized Learning Over Bipartite Graphs
.png){kind=icon}
OA
AI
DOI：10.1109/TWC.2021.3126859.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, we propose a communication-efficiently decentralized machine learning framework that solves a consensus optimization problem defined over a network of inter-connected workers. The proposed algorithm, Censored and Quantized Generalized GADMM (CQ-GGADMM), leverages the worker grouping and decentralized learning ideas of Group Alternating Direction Method of Multipliers (GADMM), and pushes the frontier in communication efficiency by extending its applicability to generalized network topologies, while incorporating link censoring for negligible updates after quantization. We theoretically prove that CQ-GGADMM achieves the linear convergence rate when the local objective functions are strongly convex under some mild assumptions. Numerical simulations corroborate that CQ-GGADMM exhibits higher communication efficiency in terms of the number of communication rounds and transmit energy consumption without compromising the accuracy and convergence speed, compared to the censored decentralized ADMM, and the worker grouping method of GADMM.
Keyword:
Convergence
Quantization (signal)
Network topology
Topology
Data models
Stochastic processes
Payloads
Alternating direction method of multipliers
communication efficiency
decentralized machine learning
stochastic quantization
期刊
IF:
10.7
论文数:
1.3W
被引数:
5.3W
机构
引用论文
Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications.png)
PROCEEDINGS OF THE IEEE
OAAI
PROCEEDINGS OF THE IEEEIF25.9
OAAI分享收藏分享收藏分享收藏Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial基于人工神经网络的无线网络机器学习: 教程OAAI
OAAI分享收藏
查看更多内容