Presentation | 2022-11-18 An Analysis of Model Parameters Propagation over Decentralized Federated Learning Koshi Eguchi, Hideya Ochiai, Hiroshi Esaki, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Although there have been many studies on Decentralized Federated Learning (DFL), few have focused on the propagation of learning results among terminal nodes. In this study, we analyzed how the learning results of each node are propagated to other nodes in DFL by changing the connection configuration of nodes, learning models, and model aggregation coefficients. By doing so, we aim to elucidate how the learning results of one node are propagated to other nodes, so that DFL can be used more efficiently. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Decentralized Federated Learning / Model Parameters / Non-IID data |
Paper # | CAS2022-51,MSS2022-34 |
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) | An Analysis of Model Parameters Propagation over Decentralized Federated Learning |
Sub Title (in English) | |
Keyword(1) | Decentralized Federated Learning |
Keyword(2) | Model Parameters |
Keyword(3) | Non-IID data |
1st Author's Name | Koshi Eguchi |
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 # | CAS2022-51,MSS2022-34 |
Volume (vol) | vol.122 |
Number (no) | CAS-253,MSS-254 |
Page | pp.pp.67-70(CAS), pp.67-70(MSS), |
#Pages | 4 |
Date of Issue | 2022-11-10 (CAS, MSS) |