| Presentation | 2022-11-24 Highly Accurate Privacy-Enhanced Federated Learning Using Data On The Server Yuta Kakizaki, Koya Sato, Keiichi Iwamura, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Federated learning is a cooperative machine learning approach that prohibits disclosing training data from distributed devices. Its privacy can be further enhanced by adding noise to the local model based on differential privacy; however, adding noise tends to decrease the training accuracy. In this paper, we focus on highly accurate privacy-enhanced federated learning schemes for situations in which each client requires a different privacy level. Specifically, we propose an adaptive model aggregation method using evaluation data on the server. According to the simulation results, the training accuracy can be improved by about 30 points in an image classification task using a convolutional neural network. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Federated Learning / Differential Privacy / Machine Learning |
| Paper # | NS2022-100 |
| Date of Issue | 2022-11-17 (NS) |
| Conference Information | |
| Committee | NS / ICM / CQ |
|---|---|
| Conference Date | 2022/11/24(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Humanities and Social Sciences Center, Fukuoka Univ. + Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Network quality, Network measurement/management, Network virtualization, Network service, Blockchain, Security, Network intelligence/AI, etc. |
| Chair | Tetsuya Oishi(NTT) / Yuji Nomura(Fujitsu) / Jun Okamoto(NTT) |
| Vice Chair | Takumi Miyoshi(Shibaura Insti of Tech.) / Yu Miyoshi(NTT) / Eiji Takahashi(NEC) / Takefumi Hiraguri(Nippon Inst. of Tech.) / Gou Hasegawa(Tohoku Univ.) |
| Secretary | Takumi Miyoshi(NTT) / Yu Miyoshi(Kogakuin Univ.) / Eiji Takahashi(NTT) / Takefumi Hiraguri(Fujitsu) / Gou Hasegawa(NTT) |
| Assistant | Kotaro Mihara(NTT) / Ryo Yamamoto(Univ. of Electro-Comm) / Kimiko Kawashima(NTT) / Ryo Nakamura(Fukuoka Univ.) / Toshiro Nakahira(NTT) / Kenta Tsukatsune(Tokyo Metroplitan Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Network Systems / Technical Committee on Information and Communication Management / Technical Committee on Communication Quality |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Highly Accurate Privacy-Enhanced Federated Learning Using Data On The Server |
| Sub Title (in English) | |
| Keyword(1) | Federated Learning |
| Keyword(2) | Differential Privacy |
| Keyword(3) | Machine Learning |
| 1st Author's Name | Yuta Kakizaki |
| 1st Author's Affiliation | Tokyo University of Science(TUS) |
| 2nd Author's Name | Koya Sato |
| 2nd Author's Affiliation | The University of Electro-Communications(UEC) |
| 3rd Author's Name | Keiichi Iwamura |
| 3rd Author's Affiliation | Tokyo University of Science(TUS) |
| Date | 2022-11-24 |
| Paper # | NS2022-100 |
| Volume (vol) | vol.122 |
| Number (no) | NS-274 |
| Page | pp.pp.1-6(NS), |
| #Pages | 6 |
| Date of Issue | 2022-11-17 (NS) |