| Presentation | 2022-11-18 Unsupervised Representation Learning over Decentralized Federated Learning Haruki Sakurai, Hideya Ochiai, Hiroshi Esaki, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Contrastive Learning is a form of self-supervised learning, a method for learning a general-purpose encoder using a large unlabeled dataset. As one of the pre-training methods, it has been actively studied since around 2020. On the other hand, it is expected to become more and more difficult to collect datasets for pre-training models as people become more privacy-conscious. Decentralized Federated Learning is one of the solution for this problem, which can learn models without sharing private data and using cetral server. In this study, we propose how Contrastive Learning can learn over Decentralized Federated Learning. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Federated Learning / Distributed Learning / Self-supervised Learning / Contrastive Learning |
| Paper # | CAS2022-54,MSS2022-37 |
| Date of Issue | 2022-11-10 (CAS, MSS) |
| Conference Information | |
| Committee | CAS / MSS / IPSJ-AL |
|---|---|
| Conference Date | 2022/11/17(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Yoshinobu Maeda(Niigata Univ.) / Atsuo Ozaki(Osaka Inst. of Tech.) / 全 眞嬉(東北大学) |
| Vice Chair | Yasutoshi Aibara(OmniVision) / Shingo Yamaguchi(Yamaguchi Univ.) |
| Secretary | Yasutoshi Aibara(NIT, Toyama college) / Shingo Yamaguchi(Renesas Electronics) / (Hokkaido Univ.) |
| Assistant | Takahide Sato(Univ. of Yamanashi) / Motoi Yamaguchi(TECHNOPRO) / Shinji Shimoda(Sony Semiconductor Solutions) / Shunsuke Koshita(Hachinohe Inst. of Tech.) / Masato Shirai(Shimane Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Circuits and Systems / Technical Committee on Mathematical Systems Science and its Applications / Special Interest Group on Algorithms |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Unsupervised Representation Learning over Decentralized Federated Learning |
| Sub Title (in English) | |
| Keyword(1) | Federated Learning |
| Keyword(2) | Distributed Learning |
| Keyword(3) | Self-supervised Learning |
| Keyword(4) | Contrastive Learning |
| Keyword(5) | |
| 1st Author's Name | Haruki Sakurai |
| 1st Author's Affiliation | The University of Tokyo(Univ. Tokyo) |
| 2nd Author's Name | Hideya Ochiai |
| 2nd Author's Affiliation | The University of Tokyo(Univ. Tokyo) |
| 3rd Author's Name | Hiroshi Esaki |
| 3rd Author's Affiliation | The University of Tokyo(Univ. Tokyo) |
| Date | 2022-11-18 |
| Paper # | CAS2022-54,MSS2022-37 |
| Volume (vol) | vol.122 |
| Number (no) | CAS-253,MSS-254 |
| Page | pp.pp.79-82(CAS), pp.79-82(MSS), |
| #Pages | 4 |
| Date of Issue | 2022-11-10 (CAS, MSS) |