Blockchained On-Device Federated Learning

Blockchained On-Device Federated Learning

By leveraging blockchain, this letter proposes a blockchained federated learning (BlockFL) architecture where local learning model updates are exchanged and verified. This enables on-device machine learning without any centralized training data or coordination by utilizing a consensus mechanism in b...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE communications letters 2020-06, Vol.24 (6), p.1279-1283
Hauptverfasser: Kim, Hyesung, Park, Jihong, Bennis, Mehdi, Kim, Seong-Lyun
Format: Artikel
Sprache:eng
Schlagworte:
Blockchain
Computational modeling
Cryptography
Data models
Delays
Federated learning
latency
Machine learning
Nickel
On-device machine learning
Servers
Training
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:By leveraging blockchain, this letter proposes a blockchained federated learning (BlockFL) architecture where local learning model updates are exchanged and verified. This enables on-device machine learning without any centralized training data or coordination by utilizing a consensus mechanism in blockchain. Moreover, we analyze an end-to-end latency model of BlockFL and characterize the optimal block generation rate by considering communication, computation, and consensus delays.
ISSN:1089-7798
1558-2558
DOI:10.1109/LCOMM.2019.2921755