CFedAvg: achieving efficient communication and fast convergence in non-iid federated learning
Federated learning (FL) is a prevailing distributed learning paradigm, where a large number
of workers jointly learn a model without sharing their training data. However, high …
of workers jointly learn a model without sharing their training data. However, high …
Semi-federated learning: Convergence analysis and optimization of a hybrid learning framework
Under the organization of the base station (BS), wireless federated learning (FL) enables
collaborative model training among multiple devices. However, the BS is merely responsible …
collaborative model training among multiple devices. However, the BS is merely responsible …
Energy-efficient clustering to address data heterogeneity in federated learning
Y Luo, X Liu, J Xiu - ICC 2021-IEEE International Conference …, 2021 - ieeexplore.ieee.org
Federated Learning (FL) is a promising distributed learning paradigm and has gained recent
attention from both academia and industry. One challenge in FL is that when local data …
attention from both academia and industry. One challenge in FL is that when local data …
Performance optimization of federated learning over wireless networks
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 …
wireless network is studied. In particular, in the considered model, wireless users perform an …
Over-the-air aggregation for federated learning: Waveform superposition and prototype validation
In this paper, we develop an orthogonal frequency-division multiplexing (OFDM)-based over-
the-air (OTA) aggregation solution for wireless federated learning (FL). In particular, the local …
the-air (OTA) aggregation solution for wireless federated learning (FL). In particular, the local …
Federated learning over noisy channels
Does Federated Learning (FL) work when both uplink and downlink communications have
errors? How much communication noise can FL handle and what is its impact to the learning …
errors? How much communication noise can FL handle and what is its impact to the learning …
Over-the-air decentralized federated learning
In this paper, we consider decentralized federated learning (FL) over wireless networks,
where over-the-air computation (AirComp) is adopted to facilitate the local model consensus …
where over-the-air computation (AirComp) is adopted to facilitate the local model consensus …
Scalable hierarchical over-the-air federated learning
SM Azimi-Abarghouyi, V Fodor - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
When implementing hierarchical federated learning over wireless networks, scalability
assurance and the ability to handle both interference and device data heterogeneity are …
assurance and the ability to handle both interference and device data heterogeneity are …
Federated learning with additional mechanisms on clients to reduce communication costs
Federated learning (FL) enables on-device training over distributed networks consisting of a
massive amount of modern smart devices, such as smartphones and IoT (Internet of Things) …
massive amount of modern smart devices, such as smartphones and IoT (Internet of Things) …
Federated learning via unmanned aerial vehicle
Federated learning (FL) has emerged as a promising alternative to centralized machine
learning for exploiting large amounts of data generated by networks while ensuring data …
learning for exploiting large amounts of data generated by networks while ensuring data …