| Presentation | 2022-05-13 Optimal Network Selection Method Using Federated Learning for Achieving Both Privacy Preservation and Large-Scale Learning Koki Horita, Akihiro Nakao, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A smartphone switches from a wireless LAN to a mobile network, including 5G, due to changes in the communication environment. Although it is useful to employ machine learning to learn a model to predict the wireless environment froma large amount of data, it is difficult to utilize data obtained from the market devices because they contain the personal information of users. In this paper, we introduce Federated Learning for learning network selection models. The model enables large-scalelearning using market data with user privacy protected and developing a model to predict the quality of the network. We evaluate the performance of these models for optimal network switching by installing them on Android devices. Our proposed methodshows that it is effective in improving user experiences by up to 400% by reducing network switching based on advance prediction. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Smartphone / Wi-Fi / Machine Learning / Federated Learning |
| Paper # | NS2022-13 |
| Date of Issue | 2022-05-05 (NS) |
| Conference Information | |
| Committee | NS |
|---|---|
| Conference Date | 2022/5/12(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Rakuyu Kaikan, Kyoto Univ. + Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | High level protocol, Networking technologies (IP and high-layer routing/filtering, Multicast, Quality/Routing control), IP network application technologies (P2P, P4P, Overlay, SIP, NGN), Network system related technologies (System configuration, Interface, Architecture, Hardware/Software/Middleware), Security, Blockchain 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) | Optimal Network Selection Method Using Federated Learning for Achieving Both Privacy Preservation and Large-Scale Learning |
| Sub Title (in English) | |
| Keyword(1) | Smartphone |
| Keyword(2) | Wi-Fi |
| Keyword(3) | Machine Learning |
| Keyword(4) | Federated Learning |
| 1st Author's Name | Koki Horita |
| 1st Author's Affiliation | Sony Corporation(Sony) |
| 2nd Author's Name | Akihiro Nakao |
| 2nd Author's Affiliation | The University of Tokyo(UTokyo) |
| Date | 2022-05-13 |
| Paper # | NS2022-13 |
| Volume (vol) | vol.122 |
| Number (no) | NS-16 |
| Page | pp.pp.23-28(NS), |
| #Pages | 6 |
| Date of Issue | 2022-05-05 (NS) |