.png){kind=icon}
返回
A Graph Neural Network Based Decentralized Learning Scheme
.png){kind=icon}
OA
AI
DOI：10.3390/s22031030.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As an emerging paradigm considering data privacy and transmission efficiency, decentralized learning aims to acquire a global model using the training data distributed over many user devices. It is a challenging problem since link loss, partial device participation, and non-independent and identically distributed (non-iid) data distribution would all deteriorate the performance of decentralized learning algorithms. Existing work may restrict to linear models or show poor performance over non-iid data. Therefore, in this paper, we propose a decentralized learning scheme based on distributed parallel stochastic gradient descent (DPSGD) and graph neural network (GNN) to deal with the above challenges. Specifically, each user device participating in the learning task utilizes local training data to compute local stochastic gradients and updates its own local model. Then, each device utilizes the GNN model and exchanges the model parameters with its neighbors to reach the average of resultant global models. The iteration repeats until the algorithm converges. Extensive simulation results over both iid and non-iid data validate the algorithm's convergence to near optimal results and robustness to both link loss and partial device participation.
Keyword:
decentralized learning
graph neural network
average consensus
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.5
论文数:
7.2W
被引数:
20.9W
机构
引用论文
Importance-Aware Data Selection and Resource Allocation in Federated Edge Learning System联邦边缘学习系统中重要度感知的数据选择与资源分配
PREAI
分享收藏Calcium chloride injection and degree of doneness effects on the sensory characteristics of beef inside round roasts.氯化钙注射液和对牛后腿烤肉的成熟度对感官特性的影响。
PREAI
分享收藏Consensus and cooperation in networked multi-agent systems网络化多智能体系统的共识与合作.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏
查看更多内容