Decentralized federated learning for extended sensing in 6G connected vehicles

Barbieri, Luca; Savazzi, Stefano; Brambilla, Mattia; Nicoli, Monica

doi:10.1016/j.vehcom.2021.100396

Cited by 59 publications

(32 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…examples E k are drawn randomly from the full training set E, while µ s is the step-size and techniques such as model pruning, sparsification [24], parameter selection and/or differential transmission schemes [12], [25] are extremely helpful to scale down the footprint b(W) in large DNNs. However, due to the great variety of compression techniques, we have considered here only a simple quantization scheme.…”

Section: Energy Footprint Modeling Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

An Energy and Carbon Footprint Analysis of Distributed and Federated Learning

Savazzi

Rampa

Kianoush

et al. 2023

IEEE Trans. on Green Commun. Netw.

Self Cite

View full text Add to dashboard Cite

Classical and centralized Artificial Intelligence (AI) methods require moving data from producers (sensors, machines) to energy hungry data centers, raising environmental concerns due to computational and communication resource demands, while violating privacy. Emerging alternatives to mitigate such high energy costs propose to efficiently distribute, or federate, the learning tasks across devices, which are typically low-power. This paper proposes a novel framework for the analysis of energy and carbon footprints in distributed and federated learning (FL). The proposed framework quantifies both the energy footprints and the carbon equivalent emissions for vanilla FL methods and consensus-based fully decentralized approaches. We discuss optimal bounds and operational points that support green FL designs and underpin their sustainability assessment. Two case studies from emerging 5G industry verticals are analyzed: these quantify the environmental footprints of continual and reinforcement learning setups, where the training process is repeated periodically for continuous improvements. For all cases, sustainability of distributed learning relies on the fulfillment of specific requirements on communication efficiency and learner population size.Energy and test accuracy should be also traded off considering the model and the data footprints for the targeted industrial applications. ො 𝑦(𝐖, ∑ ℎ 𝐱 ℎ )Data Center

show abstract

Section: Energy Footprint Modeling Frameworkmentioning

confidence: 99%

“…The energy cost for computing E are critical for sustainable designs. Notice that, as opposed to data, b(W) is roughly the same for each device, although small changes might be observed when using lossy compression, sparsification or parameter selection methods [12], [24], [25].…”

Section: B Federated Learning With Server (Fa) and Deep-sleep (Fa-d)mentioning

confidence: 99%

An Energy and Carbon Footprint Analysis of Distributed and Federated Learning

Savazzi

Rampa

Kianoush

et al. 2023

IEEE Trans. on Green Commun. Netw.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In contrast, if a blockchain system is implemented, it leverages Smart Contracts (SC) to coordinate the round delineation, model aggregation, and update tasks in FLS [130,152,184,203,254]. Lastly, if graph-based FLS is implemented, each client will utilize the graph neural network model with its neighbours to formulate the global models [15,84,143,283]. across the clients and the servers.…”

Section: Enabling Technologiesmentioning

confidence: 99%

Enabling Deep Learning for All-in EDGE paradigm

Joshi¹,

Hasanuzzaman²,

Thapa³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep Learning-based models have been widely investigated, and they have demonstrated significant performance on non-trivial tasks such as speech recognition, image processing, and natural language understanding. However, this is at the cost of substantial data requirements. Considering the widespread proliferation of edge devices (e.g., Internet of Things devices) over the last decade, Deep Learning in the edge paradigm, such as device-cloud integrated platforms, is required to leverage its superior performance. Moreover, it is suitable from the data requirements perspective in the edge paradigm because the proliferation of edge devices has resulted in an explosion in the volume of generated and collected data. However, there are difficulties due to other requirements such as high computation, high latency, and high bandwidth caused by Deep Learning applications in real-world scenarios. In this regard, this survey paper investigates Deep Learning at the edge, its architecture, enabling technologies, and model adaption techniques, where edge servers and edge devices participate in deep learning training and inference. For simplicity, we call this paradigm the All-in EDGE paradigm. Besides, this paper presents the key performance metrics for Deep Learning at the All-in EDGE paradigm to evaluate various deep learning techniques and choose a suitable design. Moreover, various open challenges arising from the deployment of Deep Learning at the All-in EDGE paradigm are identified and discussed.

show abstract

“…The authors in [42] used FL to predict the turning signal. More recently, the authors in [43], [44] used FL for 6G-enabled autonomous cars. Peng et al [45] introduced an adaptive FL framework for autonomous vehicles.…”

Section: Related Workmentioning

confidence: 99%

Deep Federated Learning for Autonomous Driving

Nguyen¹,

Do²,

Tran³

et al. 2021

Preprint

View full text Add to dashboard Cite

Autonomous driving is an active research topic in both academia and industry. However, most of the existing solutions focus on improving the accuracy by training learnable models with centralized large-scale data. Therefore, these methods do not take into account the user's privacy. In this paper, we present a new approach to learn autonomous driving policy while respecting privacy concerns. We propose a peer-to-peer Deep Federated Learning (DFL) approach to train deep architectures in a fully decentralized manner and remove the need for central orchestration. We design a new Federated Autonomous Driving network (FADNet) that can improve the model stability, ensure convergence, and handle imbalanced data distribution problems while is being trained with federated learning methods. Intensively experimental results on three datasets show that our approach with FADNet and DFL achieves superior accuracy compared with other recent methods. Furthermore, our approach can maintain privacy by not collecting user data to a central server. Our source code and trained models are available at https://github.com/aioz-ai/FADNet

show abstract

Decentralized federated learning for extended sensing in 6G connected vehicles

Cited by 59 publications

References 63 publications

An Energy and Carbon Footprint Analysis of Distributed and Federated Learning

An Energy and Carbon Footprint Analysis of Distributed and Federated Learning

Enabling Deep Learning for All-in EDGE paradigm

Deep Federated Learning for Autonomous Driving

Contact Info

Product

Resources

About