YiPeng Zhou
Washington State University
25 Papers
4 Citations
YiPeng Zhou is an academic researcher from Washington State University. The author has contributed to research in topics: Computer science & Communications system. The author has an hindex of 1, co-authored 1 publications.
Chat about Author
Papers
On Model Transmission Strategies in Federated Learning With Lossy Communications
TL;DR: In this paper , the convergence rate of federated learning with lossy communications was derived under non-convex loss with the optimal transmission, and the authors presented effective practical solutions.
19
A Fast Blockchain-Based Federated Learning Framework With Compressed Communications
TL;DR: A fast blockchain-based communication-efficient federated learning framework by compressing communications in BFL, called BCFL, and formulate the problem to minimize the training loss of the convergence rate subject to a limited training time with respect to the compression rate and the block generation rate, which is a bi-convex optimization problem.
17
AutoFL: A Bayesian Game Approach for Autonomous Client Participation in Federated Edge Learning
TL;DR: Li et al. as mentioned in this paper proposed an autonomous client participation decision framework for federated learning at the network edge without assuming that each client possesses complete information, where each player in the game is associated with a set of types according to network conditions.
12
pFedSim: Similarity-Aware Model Aggregation Towards Personalized Federated Learning
TL;DR: Li et al. as discussed by the authors proposed a novel pFedSim (pFL based on model similarity) algorithm by combining similarity-based aggregation and model decoupling, which decouple a neural network (NN) model into a feature extractor and a classifier.
9
A Survey of Federated Evaluation in Federated Learning
TL;DR: A comprehensive survey of federated evaluation methods for machine learning can be found in this paper , where the authors explore various applications and future research directions by envisioning some challenges, including client selection, incentive mechanism design and malicious attack detection.
8