Jeong, E., Oh, S., Park, J., Kim, H., Bennis, M., Kim, S-S., Multi-hop federated private data augmentation with sample compression, https://arxiv.org/abs/1907.06426
Multi-hop federated private data augmentation with sample compression
|Author:||Jeong, Eunjeong1; Oh, Seungeun1; Park, Jihong2;|
1Electrical and Electronic Engineering, Yonsei University, Seoul, Korea
2Centre for Wireless Communications, University of Oulu, Finland
|Online Access:||PDF Full Text (PDF, 2.9 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2020102787867
|Publish Date:|| 2020-10-27
On-device machine learning (ML) has brought about the accessibility to a tremendous amount of data from the users while keeping their local data private instead of storing it in a central entity. However, for privacy guarantee, it is inevitable at each device to compensate for the quality of data or learning performance, especially when it has a non-IID training dataset. In this paper, we propose a data augmentation framework using a generative model: multi-hop federated augmentation with sample compression (MultFAug). A multi-hop protocol speeds up the end-to-end over-the-air transmission of seed samples by enhancing the transport capacity. The relaying devices guarantee stronger privacy preservation as well since the origin of each seed sample is hidden in those participants. For further privatization on the individual sample level, the devices compress their data samples. The devices sparsify their data samples prior to transmissions to reduce the sample size, which impacts the communication payload. This preprocessing also strengthens the privacy of each sample, which corresponds to the input perturbation for preserving sample privacy. The numerical evaluations show that the proposed framework significantly improves privacy guarantee, transmission delay, and local training performance with adjustment to the number of hops and compression rate.
|Pages:||1 - 8|
28th International Joint Conference on Artificial Intelligence (IJCAI-19), 1st International Workshop on Federated Machine Learning for User Privacy and Data Confidentiality (FML'19), Macao, China
International Joint Conference on Artificial Intelligence
|Field of Science:||
213 Electronic, automation and communications engineering, electronics
This research was supported partly by Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Science and ICT(NRF-2017R1A2A2A05069810), partly by Academy of Finland projects SMARTER, CARMA, and 6Genesis Flagship (grant no. 318927), and partly by AIMS and ELLIS projects at the University of Oulu.
|Academy of Finland Grant Number:||
318927 (Academy of Finland Funding decision)
© The Authors 2019.