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
Adaptive Control of Local Updating and Model Compression for Efficient Federated Learning
TL;DR: In this article , a training-efficient federated learning (FL) method, termed FedLamp, was proposed by optimizing both the Local updating frequency and model compression ratio in the resource-constrained EC systems.
Journal ArticleDOI
Joint Training and Resource Allocation Optimization for Federated Learning in UAV Swarm
TL;DR: Considering the limited energy supply of UAVs, Wang et al. as mentioned in this paper studied how to minimize the overall training energy consumption by jointly optimizing the local convergence threshold, local iterations, computation resource allocation, and bandwidth allocation, subject to the FL global accuracy guarantee and maximum training latency constraint.
Journal ArticleDOI
On the crowdsourcing of behaviors for autonomous agents
TL;DR: In this article, the problem of designing, from data, agents that are able to craft their behavior from a number of contributors in order to fulfill some agent-specific task is addressed.
Journal ArticleDOI
CLONE: Collaborative Learning on the Edges
Sidi Lu,Yongtao Yao,Weisong Shi +2 more
TL;DR: Li et al. as mentioned in this paper proposed a collaborative learning framework on the edges, which is steered by the real-world data sets collected from a large electric vehicle (EV) company and a grocery store of a shopping mall, respectively.
Journal ArticleDOI
Knowledge-Guided Learning for Transceiver Design in Over-the-Air Federated Learning
TL;DR: This paper derives the upper bound of the time-average norm of the gradients to characterize the convergence of AirComp-assisted FL, which reveals the impact of the model aggregation errors accumulated over all communication rounds on convergence.