Consensus driven on-device hyperparameter optimization for accelerated model convergence in decentralized federated learning
Abstract Decentralized Federated Learning (DFL) enables collaborative model training
across multiple devices without relying on a central server, thus preserving data privacy and …
across multiple devices without relying on a central server, thus preserving data privacy and …
Dynamic and Fast Convergence for Federated Learning via Optimized Hyperparameters
X Yu, Y Lin, Z Gao, H Du… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Federated Learning (FL) is a privacy-preserving computing paradigm that enables
participants to collaboratively train a global model without exchanging their raw personal …
participants to collaboratively train a global model without exchanging their raw personal …
CAFe: Cost and Age aware Federated Learning
S Liyanaarachchi, K Thilakarathna… - Proceedings of the Twenty …, 2024 - dl.acm.org
In many federated learning (FL) models, a common strategy employed to ensure the
progress in the training process, is to wait for at least M clients out of the total N clients to …
progress in the training process, is to wait for at least M clients out of the total N clients to …
An Efficient Asynchronous Federated Learning Protocol for Edge Devices
Q Li, Z Gao, Y Sun, Y Wang, R Wang… - IEEE Internet of Things …, 2024 - ieeexplore.ieee.org
Recent studies highlight the significant potential of edge computing and federated learning
in advancing artificial intelligence. However, challenges such as unstable device …
in advancing artificial intelligence. However, challenges such as unstable device …
Federated Learning-Based Distributed Model Predictive Control of Nonlinear Systems
This work develops a federated learning-based distributed model predictive control (FL-
DMPC) method for nonlinear systems with multiple subsystems to address the privacy …
DMPC) method for nonlinear systems with multiple subsystems to address the privacy …