| Presentation | 2021-10-08 A study of privacy-preserving distributed machine learning using Rich Clients Saki Takano, Akihiro Nakao, Saneyasu Yamaguchi, Masato Oguchi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, edge computing has attracted much attention because of its advantages such as low latency and the ability to distribute the load on the network. However, the conventional method of transferring data to the edge server for training cannot be used for training personal data, which is highly sensitive and should not be taken out from the device. In this study, we consider a distributed machine learning model suitable for rich clients that work with the edge server and also run machine learning on the device. In this paper, we propose a training model that continues to learn on the edge device from the results trained on the edge server, and conduct experiments using the Jetson Nano. We have confirmed that high accuracy can be achieved by providing some general data in addition to personal data for training on the edge device. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Edge Computing / Distributed Machine Learning / Federated learning / Machine Learning / Internet of Things |
| Paper # | NS2021-76 |
| Date of Issue | 2021-09-29 (NS) |
| Conference Information | |
| Committee | NS |
|---|---|
| Conference Date | 2021/10/6(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Network architecture (Overlay, P2P, Ubiquitous network, Scale-free network, Active network, NGN/NwGN, IoT, Edge computing, Next generation packet transport (High speed Ethernet, IP over WDM, Multi-service package technology, MPLS), Grid, etc. |
| Chair | Akihiro Nakao(Univ. of Tokyo) |
| Vice Chair | Tetsuya Oishi(NTT) |
| Secretary | Tetsuya Oishi(NTT) |
| Assistant | Kotaro Mihara(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Network Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A study of privacy-preserving distributed machine learning using Rich Clients |
| Sub Title (in English) | |
| Keyword(1) | Edge Computing |
| Keyword(2) | Distributed Machine Learning |
| Keyword(3) | Federated learning |
| Keyword(4) | Machine Learning |
| Keyword(5) | Internet of Things |
| 1st Author's Name | Saki Takano |
| 1st Author's Affiliation | Ochanomizu University(Ochanomizu Univ.) |
| 2nd Author's Name | Akihiro Nakao |
| 2nd Author's Affiliation | The University of Tokyo(The Univ. of Tokyo) |
| 3rd Author's Name | Saneyasu Yamaguchi |
| 3rd Author's Affiliation | Kogakuin University(Kogakuin Univ.) |
| 4th Author's Name | Masato Oguchi |
| 4th Author's Affiliation | Ochanomizu University(Ochanomizu Univ.) |
| Date | 2021-10-08 |
| Paper # | NS2021-76 |
| Volume (vol) | vol.121 |
| Number (no) | NS-185 |
| Page | pp.pp.45-50(NS), |
| #Pages | 6 |
| Date of Issue | 2021-09-29 (NS) |