Title
Distributed Heuristic Adaptive Neural Networks With Variance Reduction in Switching Graphs.
Abstract
This article proposes a distributed adaptive training method for neural networks in switching communication graphs to deal with the problems concerned with massive data or privacy-related data. First, the stochastic variance reduced gradient (SVRG) is used for the training of neural networks. Then, the authors propose a heuristic adaptive consensus algorithm for distributed training, which adaptiv...
Year
DOI
Venue
2021
10.1109/TCYB.2019.2956291
IEEE Transactions on Cybernetics
Keywords
DocType
Volume
Neural networks,Training,Consensus algorithm,Convergence,Topology,Stochastic processes,Computational modeling
Journal
51
Issue
ISSN
Citations 
7
2168-2267
0
PageRank 
References 
Authors
0.34
0
2
Name
Order
Citations
PageRank
Bo Liu101.35
Zhengtao Ding2315.53