University of Oulu

E. Jeong, S. Oh, J. Park, H. Kim, M. Bennis and S. -L. Kim, "Hiding in the Crowd: Federated Data Augmentation for On-Device Learning," in IEEE Intelligent Systems, vol. 36, no. 5, pp. 80-87, 1 Sept.-Oct. 2021, doi: 10.1109/MIS.2020.3028613

Hiding in the crowd : federated data augmentation for on-device learning

Saved in:
Author: Jeong, Eunjeong1; Oh, Seungeun1; Park, Jihong2;
Organizations: 1Yonsei University, Seoul, Korea
2Deakin University, Victoria, Australia
3Samsung Research, Seoul, Korea
4University of Oulu, Oulu, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 1 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe2021122162702
Language: English
Published: Institute of Electrical and Electronics Engineers, 2021
Publish Date: 2021-12-21
Description:

Abstract

To cope with the lack of on-device machine learning samples, this article presents a distributed data augmentation algorithm, coined federated data augmentation (FAug). In FAug, devices share a tiny fraction of their local data, i.e., seed samples, and collectively train a synthetic sample generator that can augment the local datasets of devices. To further improve FAug, we introduce a multihop-based seed sample collection method and an oversampling technique that mixes up collected seed samples. Both approaches enjoy the benefit from the crowd of devices, by hiding data privacy from preceding hops and feeding diverse seed samples. In the image classification tasks, simulations demonstrate that the proposed FAug frameworks yield stronger privacy guarantees, lower communication latency, and higher on-device ML accuracy.

see all

Series: IEEE intelligent systems
ISSN: 1541-1672
ISSN-E: 1941-1294
ISSN-L: 1541-1672
Volume: 36
Issue: 5
Pages: 80 - 87
DOI: 10.1109/MIS.2020.3028613
OADOI: https://oadoi.org/10.1109/MIS.2020.3028613
Type of Publication: A1 Journal article – refereed
Field of Science: 213 Electronic, automation and communications engineering, electronics
Subjects:
Funding: This research was supported by a grant to Bio-Mimetic Robot Research Center Funded by Defense Acquisition Program Administration, and by Agency for Defense Development (UD190018ID).
Copyright information: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.