Federated Learning Over Wireless Device-to-Device Networks: Algorithms and Convergence Analysis

The proliferation of Internet-of-Things (IoT) devices and cloud-computing applications over siloed data centers is motivating renewed interest in the collaborative training of a shared model by multiple individual clients via federated learning (FL). To improve the communication efficiency of FL imp...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE journal on selected areas in communications Ročník 39; číslo 12; s. 3723 - 3741
Hlavní autoři: Xing, Hong, Simeone, Osvaldo, Bi, Suzhi
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.12.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Algorithms
Channel noise
Clients
Cloud computing
Collaborative work
Convergence
Convexity
D2D networks
Data centers
Data models
decentralized stochastic gradient descent
Device-to-device communication
distributed learning
Federated learning
Image classification
Internet of Things
Machine learning
over-the-air computation
random linear coding
Signal to noise ratio
Stochastic processes
Topology
Wireless communications
Wireless networks
ISSN:0733-8716, 1558-0008
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The proliferation of Internet-of-Things (IoT) devices and cloud-computing applications over siloed data centers is motivating renewed interest in the collaborative training of a shared model by multiple individual clients via federated learning (FL). To improve the communication efficiency of FL implementations in wireless systems, recent works have proposed compression and dimension reduction mechanisms, along with digital and analog transmission schemes that account for channel noise, fading, and interference. The prior art has mainly focused on star topologies consisting of distributed clients and a central server. In contrast, this paper studies FL over wireless device-to-device (D2D) networks by providing theoretical insights into the performance of digital and analog implementations of decentralized stochastic gradient descent (DSGD). First, we introduce generic digital and analog wireless implementations of communication-efficient DSGD algorithms, leveraging random linear coding (RLC) for compression and over-the-air computation (AirComp) for simultaneous analog transmissions. Next, under the assumptions of convexity and connectivity, we provide convergence bounds for both implementations. The results demonstrate the dependence of the optimality gap on the connectivity and on the signal-to-noise ratio (SNR) levels in the network. The analysis is corroborated by experiments on an image-classification task.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0733-8716
1558-0008
DOI:10.1109/JSAC.2021.3118400