FedKL: Tackling data heterogeneity in federated reinforcement learning by penalizing KL divergence

Z Xie, S Song - IEEE Journal on Selected Areas in …, 2023 - ieeexplore.ieee.org
One of the fundamental issues for Federated Learning (FL) is data heterogeneity, which
causes accuracy degradation, slow convergence, and the communication bottleneck issue …

Finite-time analysis of on-policy heterogeneous federated reinforcement learning

C Zhang, H Wang, A Mitra, J Anderson - arXiv preprint arXiv:2401.15273, 2024 - arxiv.org
Federated reinforcement learning (FRL) has emerged as a promising paradigm for reducing
the sample complexity of reinforcement learning tasks by exploiting information from …

Fault-tolerant federated reinforcement learning with theoretical guarantee

X Fan, Y Ma, Z Dai, W Jing, C Tan… - Advances in Neural …, 2021 - proceedings.neurips.cc
The growing literature of Federated Learning (FL) has recently inspired Federated
Reinforcement Learning (FRL) to encourage multiple agents to federatively build a better …

Fusion of global and local knowledge for personalized federated learning

T Huang, L Shen, Y Sun, W Lin, D Tao - arXiv preprint arXiv:2302.11051, 2023 - arxiv.org
Personalized federated learning, as a variant of federated learning, trains customized
models for clients using their heterogeneously distributed data. However, it is still …

Performance optimization of federated learning over wireless networks

M Chen, Z Yang, W Saad, C Yin… - 2019 IEEE global …, 2019 - ieeexplore.ieee.org
In this paper, the problem of training federated learning (FL) algorithms over a realistic
wireless network is studied. In particular, in the considered model, wireless users perform an …

Adaptive hierarchical federated learning over wireless networks

B Xu, W Xia, W Wen, P Liu, H Zhao… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Federated learning (FL) is promising in enabling large-scale model training by massive
devices without exposing their local datasets. However, due to limited wireless resources …

Fedlga: Toward system-heterogeneity of federated learning via local gradient approximation

X Li, Z Qu, B Tang, Z Lu - IEEE Transactions on Cybernetics, 2023 - ieeexplore.ieee.org
Federated learning (FL) is a decentralized machine learning architecture, which leverages a
large number of remote devices to learn a joint model with distributed training data …

Robust federated learning with noisy communication

F Ang, L Chen, N Zhao, Y Chen… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Federated learning is a communication-efficient training process that alternate between
local training at the edge devices and averaging of the updated local model at the center …

Convergence time minimization of federated learning over wireless networks

M Chen, HV Poor, W Saad, S Cui - ICC 2020-2020 IEEE …, 2020 - ieeexplore.ieee.org
In this paper, the convergence time of federated learning (FL), when deployed over a
realistic wireless network, is studied. In particular, with the considered model, wireless users …

Adaptive model pruning for communication and computation efficient wireless federated learning

Z Chen, W Yi, H Shin… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Most existing wireless federated learning (FL) studies focused on homogeneous model
settings where devices train identical local models. In this setting, the devices with poor …