FedDQ: Communication-efficient federated learning with descending quantization

L Qu, S Song, CY Tsui - GLOBECOM 2022-2022 IEEE Global …, 2022 - ieeexplore.ieee.org
Federated learning (FL) is an emerging learning paradigm without violating users' privacy.
However, large model size and frequent model aggregation cause serious communication …

Wireless quantized federated learning: A joint computation and communication design

PS Bouzinis, PD Diamantoulakis… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Recently, federated learning (FL) has sparked widespread attention as a promising
decentralized machine learning approach which provides privacy and low delay. However …

Wireless federated learning with asynchronous and quantized updates

P Huang, D Li, Z Yan - IEEE Communications Letters, 2023 - ieeexplore.ieee.org
Federated learning (FL) is a framework of large-scale distributed learning with user privacy
protection through local training and global aggregation. However, FL may suffer from …

Fedlp: Layer-wise pruning mechanism for communication-computation efficient federated learning

Z Zhu, Y Shi, J Luo, F Wang, C Peng… - ICC 2023-IEEE …, 2023 - ieeexplore.ieee.org
Federated learning (FL) has prevailed as an efficient and privacy-preserved scheme for
distributed learning. In this work, we mainly focus on the optimization of computation and …

[HTML][HTML] Rate distortion optimization for adaptive gradient quantization in federated learning

G Chen, K Xie, W Luo, Y Xu, L Xin, T Song… - Digital Communications …, 2024 - Elsevier
Federated Learning (FL) is an emerging machine learning framework designed to preserve
privacy. However, the continuous updating of model parameters over uplink channels with …

Communication-efficient federated learning with adaptive quantization

Y Mao, Z Zhao, G Yan, Y Liu, T Lan, L Song… - ACM Transactions on …, 2022 - dl.acm.org
Federated learning (FL) has attracted tremendous attentions in recent years due to its
privacy-preserving measures and great potential in some distributed but privacy-sensitive …

Quantized federated learning under transmission delay and outage constraints

Y Wang, Y Xu, Q Shi, TH Chang - IEEE Journal on Selected …, 2021 - ieeexplore.ieee.org
Federated learning (FL) has been recognized as a viable distributed learning paradigm
which trains a machine learning model collaboratively with massive mobile devices in the …

ClusterGrad: Adaptive gradient compression by clustering in federated learning

L Cui, X Su, Y Zhou, L Zhang - GLOBECOM 2020-2020 IEEE …, 2020 - ieeexplore.ieee.org
Recently, Federated Learning (FL) has drawn tremendous attentions due to its ability to
protect client's privacy. In FL, clients collaboratively train machine learning models by merely …

Latency-efficient wireless federated learning with quantization and scheduling

Z Yan, D Li, X Yu, Z Zhang - IEEE Communications Letters, 2022 - ieeexplore.ieee.org
Federated learning (FL) protects data privacy through local training and parameter
aggregation. However, there is no need that all users are required to train their local models …

GIFT: Toward accurate and efficient federated learning with gradient-instructed frequency tuning

C Chen, H Xu, W Wang, B Li, B Li… - IEEE Journal on …, 2023 - ieeexplore.ieee.org
Federated learning (FL) enables distributed clients to collectively train a global model
without revealing their private data, and for efficiency clients synchronize their gradients …