Results 21 to 30 of about 6,308,360 (314)
Heterogeneous Federated Learning
CoRR, 2020 Full version [Fed2: Feature-Aligned Federated Learning] accepted in KDD ...
Fuxun Yu +7 more
openaire +2 more sources
Hybrid Federated and Centralized Learning [PDF]
2021 29th European Signal Processing Conference (EUSIPCO), 2021 Many of the machine learning (ML) tasks are focused on centralized learning (CL), which requires the transmission of local datasets from the clients to a parameter server (PS) leading to a huge communication overhead. Federated learning (FL) overcomes this issue by allowing the clients to send only the model updates to the PS instead of the whole ...
Ahmet M. Elbir +2 more
openaire +3 more sources
2022 International Joint Conference on Neural Networks (IJCNN), 2022 To be published in IEEE IJCNN 2022 ...
Kuo-Yun Liang +2 more
openaire +4 more sources
Certified Robustness in Federated Learning [PDF]
, 2022 Federated learning has recently gained significant attention and popularity due to its effectiveness in training machine learning models on distributed data privately.
Richtarik, Peter +4 more
core
On a Framework for Federated Cluster Analysis
Applied Sciences, 2022 Federated learning is becoming increasingly popular to enable automated learning in distributed networks of autonomous partners without sharing raw data.
Morris Stallmann, Anna Wilbik
doaj +1 more source
Preconditioned Federated Learning
CoRR, 2023 Federated Learning (FL) is a distributed machine learning approach that enables model training in communication efficient and privacy-preserving manner. The standard optimization method in FL is Federated Averaging (FedAvg), which performs multiple local SGD steps between communication rounds.
Zeyi Tao, Jindi Wu, Qun Li 0001
openaire +3 more sources
Blind Federated Edge Learning [PDF]
IEEE Transactions on Wireless Communications, 2021 submitted for publication.
Mohammad Mohammadi Amiri +4 more
openaire +6 more sources
JMIR Medical Informatics, 2021 BackgroundFederated learning is a decentralized approach to machine learning; it is a training strategy that overcomes medical data privacy regulations and generalizes deep learning algorithms.
Lee, Haeyun +15 more
doaj +1 more source
Coded Federated Learning [PDF]
2019 IEEE Globecom Workshops (GC Wkshps), 2019 Federated learning is a method of training a global model from decentralized data distributed across client devices. Here, model parameters are computed locally by each client device and exchanged with a central server, which aggregates the local models for a global view, without requiring sharing of training data.
Sagar Dhakal +4 more
openaire +3 more sources
CoRR, 2019 Federated Learning allows for population level models to be trained without centralizing client data by transmitting the global model to clients, calculating gradients locally, then averaging the gradients. Downloading models and uploading gradients uses the client's bandwidth, so minimizing these transmission costs is important.
Jack Goetz +5 more
openaire +3 more sources