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
Decentralized Aggregation for Energy-Efficient Federated Learning via D2D Communications
TL;DR: In this article , a federated learning empowered overlapped clustering for decentralized aggregation (FL-EOCD) scheme is proposed, where the aggregated models of each cluster are disseminated to other clusters in a decentralized manner without the need for a global aggregator or an additional hop of transmission.
Posted Content
Optimization-Based GenQSGD for Federated Edge Learning
TL;DR: In this article, a general quantized parallel mini-batch stochastic gradient descent (SGD) algorithm for federated learning (FL) is presented, which is parameterized by the number of global iterations, the numbers of local iterations at all workers, and the minibatch size.
Journal ArticleDOI
FedProf: Selective Federated Learning Based on Distributional Representation Profiling
TL;DR: FedProf as mentioned in this paper proposes a distributional representation profiling and matching scheme that uses the global model to dynamically profile data representations and allows for low-cost, lightweight representation matching to mitigate the impact of low-quality data on the training process.
Journal ArticleDOI
Backdoor Attacks in Peer-to-Peer Federated Learning
TL;DR: In this paper , the authors proposed new backdoor attacks for P2PFL that leverage structural graph properties to select the malicious nodes, and achieve high attack success, while remaining stealthy, and evaluate their attacks under various realistic conditions, including multiple graph topologies, limited adversarial visibility of the network, and clients with non-IID data.