Adaptive Federated Learning in Resource Constrained Edge Computing Systems
Shiqiang Wang,Tiffany Tuor,Theodoros Salonidis,Kin K. Leung,Christian Makaya,Ting He,Kevin S. Chan +6 more
Reads0
Chats0
TLDR
In this paper, the authors consider the problem of learning model parameters from data distributed across multiple edge nodes, without sending raw data to a centralized place, and propose a control algorithm that determines the best tradeoff between local update and global parameter aggregation to minimize the loss function under a given resource budget.Abstract:
Emerging technologies and applications including Internet of Things, social networking, and crowd-sourcing generate large amounts of data at the network edge. Machine learning models are often built from the collected data, to enable the detection, classification, and prediction of future events. Due to bandwidth, storage, and privacy concerns, it is often impractical to send all the data to a centralized location. In this paper, we consider the problem of learning model parameters from data distributed across multiple edge nodes, without sending raw data to a centralized place. Our focus is on a generic class of machine learning models that are trained using gradient-descent-based approaches. We analyze the convergence bound of distributed gradient descent from a theoretical point of view, based on which we propose a control algorithm that determines the best tradeoff between local update and global parameter aggregation to minimize the loss function under a given resource budget. The performance of the proposed algorithm is evaluated via extensive experiments with real datasets, both on a networked prototype system and in a larger-scale simulated environment. The experimentation results show that our proposed approach performs near to the optimum with various machine learning models and different data distributions.read more
Citations
More filters
Journal ArticleDOI
Communication-efficient Federated Edge Learning via Optimal Probabilistic Device Scheduling
TL;DR: An optimized probabilistic device scheduling policy is derived in closed-form by solving the approximate communication time minimization problem and it is found that the optimized policy gradually turns its priority from suppressing the remaining communication rounds to reducing per-round latency as the training process evolves.
Posted Content
FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout
Samuel Horváth,Stefanos Laskaridis,Mario Almeida,Ilias Leontiadis,Stylianos I. Venieris,Nicholas D. Lane +5 more
TL;DR: In this paper, Ordered Dropout, a mechanism that achieves an ordered, nested representation of knowledge in Neural Networks and enables the extraction of lower footprint submodels without the need of retraining, is introduced.
Journal ArticleDOI
Low-Latency Federated Learning Over Wireless Channels With Differential Privacy
TL;DR: In this paper , a multi-agent multi-armed bandit (MAMAB) framework is proposed to minimize FL training delay over wireless channels, constrained by overall training performance as well as each client's differential privacy requirement.
Journal ArticleDOI
Machine learning in vehicular networking: an overview
TL;DR: In this paper, a short survey of ML applications in vehicular networks from the networking aspect is provided, including network control containing handover management and routing decision making, resource management, and energy efficiency.
Journal ArticleDOI
E-Tree Learning: A Novel Decentralized Model Learning Framework for Edge AI
TL;DR: Wang et al. as discussed by the authors proposed a decentralized model learning approach, namely, E-Tree, which makes use of a well-designed tree structure imposed on the edge devices to improve the training convergence and model accuracy.