Multi-hop Federated Private Data Augmentation with Sample Compression
By Eunjeong Jeong, Seungeun Oh, Jihong Park, Hyesung Kim, Medhi Bennis, Seong-Lyun Kim. 2019
19 citations recorded by the source corpus.
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.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Jihong Park
- Medhi Bennis
- Sumudu Samarakoon
- Anis Elgabli
- Merouane Debbah
- Hyesung Kim
- Eunjeong Jeong
- Shiqiang Wang
Citations in the corpus
- Wireless Network Intelligence at the Edge (2018, background): “Its impact on FAug is elaborated in [215].”
- Distilling On-Device Intelligence at the Network Edge (2019, background): “Multi-hop federated data augmentation with sample compression (MultFAug) [15] preserves such target label and sample privacy while maximizing communication efficiency as detailed next.”
- Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications (2020, background): “For example, to rectify non-IID data distributions, each worker can exchange mixed-up samples or manifold mixed-up representations to complement missing samples in some labels [142].”