Private and communication-efficient edge learning: a sparse differential gaussian-masking distributed SGD approach
With the rise of machine learning (ML) and the proliferation of smart mobile devices, recent
years have witnessed a surge of interest in performing ML in wireless edge networks. In this …
years have witnessed a surge of interest in performing ML in wireless edge networks. In this …
Wireless federated distillation for distributed edge learning with heterogeneous data
Cooperative training methods for distributed machine learning typically assume noiseless
and ideal communication channels. This work studies some of the opportunities and …
and ideal communication channels. This work studies some of the opportunities and …
Privacy for free: Wireless federated learning via uncoded transmission with adaptive power control
Federated Learning (FL) refers to distributed protocols that avoid direct raw data exchange
among the participating devices while training for a common learning task. This way, FL can …
among the participating devices while training for a common learning task. This way, FL can …
Distributed learning over a wireless network with non-coherent majority vote computation
A Şahin - IEEE Transactions on Wireless Communications, 2023 - ieeexplore.ieee.org
In this study, we propose an over-the-air computation (OAC) scheme to calculate the
majority vote (MV) for federated edge learning (FEEL). With the proposed approach, edge …
majority vote (MV) for federated edge learning (FEEL). With the proposed approach, edge …
Decentralized federated learning with unreliable communications
Decentralized federated learning, inherited from decentralized learning, enables the edge
devices to collaborate on model training in a peer-to-peer manner without the assistance of …
devices to collaborate on model training in a peer-to-peer manner without the assistance of …
Federated learning and next generation wireless communications: A survey on bidirectional relationship
In order to meet the extremely heterogeneous requirements of the next generation wireless
communication networks, research community is increasingly dependent on using machine …
communication networks, research community is increasingly dependent on using machine …
Federated learning over wireless fading channels
We study federated machine learning at the wireless network edge, where limited power
wireless devices, each with its own dataset, build a joint model with the help of a remote …
wireless devices, each with its own dataset, build a joint model with the help of a remote …
Decentralized federated learning via SGD over wireless D2D networks
Federated Learning (FL), an emerging paradigm for fast intelligent acquisition at the network
edge, enables joint training of a machine learning model over distributed data sets and …
edge, enables joint training of a machine learning model over distributed data sets and …
Distributed learning over a wireless network with FSK-based majority vote
In this study, we propose an over-the-air computation (AirComp) scheme for federated edge
learning (FEEL). The proposed scheme relies on the concept of distributed learning by …
learning (FEEL). The proposed scheme relies on the concept of distributed learning by …
Laplacian matrix sampling for communication-efficient decentralized learning
We consider the problem of training a given machine learning model by decentralized
parallel stochastic gradient descent over training data distributed across multiple nodes …
parallel stochastic gradient descent over training data distributed across multiple nodes …