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 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.

Authors:
Kim Hyesung, Park Jihong, Bennis Mehdi, Kim Seong-Lyun

Publication type:
A1 Journal article – refereed

Place of publication:

Keywords:
blockchain, federated learning, latency, On-device machine learning

Published:

Full citation:
H. Kim, J. Park, M. Bennis and S. Kim, “Blockchained On-Device Federated Learning,” in IEEE Communications Letters, vol. 24, no. 6, pp. 1279-1283, June 2020, doi: 10.1109/LCOMM.2019.2921755

DOI:
https://doi.org/10.1109/LCOMM.2019.2921755

Read the publication here:
http://urn.fi/urn:nbn:fi-fe2019120946269