| 講演名 | 2022-03-04 [Invited Talk] Fuzzy Logic-based Client Selection for Federated Learning in Vehicular IoT 策力 木格(電通大), |
|---|---|
| PDFダウンロードページ |  PDFダウンロードページへ |
| 抄録(和) | In order to support advanced vehicular Internet-of-Things applications, information exchanges among different vehicles are required to find efficient solutions for catering to different application requirements in complex and dynamic vehicular environments. Federated learning (FL), which is a type of distributed learning technology, has been attracting great interest in recent years as it performs knowledge exchange among different network entities without a violation of user privacy. This talk will discuss about the problem of how to achieve an efficient client selection to improve the learning performance of FL. We propose a fuzzy logic based client selection scheme to address this issue. The proposed scheme considers the number of local samples, the samples freshness, the computation capability, and the available communication resources based on a fuzzy logic approach. Extensive simulation results show that the proposed scheme outperforms other baselines. |
| 抄録(英) | In order to support advanced vehicular Internet-of-Things applications, information exchanges among different vehicles are required to find efficient solutions for catering to different application requirements in complex and dynamic vehicular environments. Federated learning (FL), which is a type of distributed learning technology, has been attracting great interest in recent years as it performs knowledge exchange among different network entities without a violation of user privacy. This talk will discuss about the problem of how to achieve an efficient client selection to improve the learning performance of FL. We propose a fuzzy logic based client selection scheme to address this issue. The proposed scheme considers the number of local samples, the samples freshness, the computation capability, and the available communication resources based on a fuzzy logic approach. Extensive simulation results show that the proposed scheme outperforms other baselines. |
| キーワード(和) | |
| キーワード(英) | Federated learningClient selectionFuzzy logicVehicular IoT |
| 資料番号 | ICM2021-50 |
| 発行日 | 2022-02-24 (ICM) |
| 研究会情報 | |
| 研究会 | ICM |
|---|---|
| 開催期間 | 2022/3/3(から2日開催) |
| 開催地（和） | オンライン開催 |
| 開催地（英） | Online |
| テーマ（和） | エレメント管理，管理機能，理論・運用方法論，一般 |
| テーマ（英） | |
| 委員長氏名（和） | 木下 和彦(徳島大) |
| 委員長氏名（英） | Kazuhiko Kinoshita(Tokushima Univ.) |
| 副委員長氏名（和） | 大石 晴夫(NTT) / 高橋 英士(NEC) |
| 副委員長氏名（英） | Haruo Ooishi(NTT) / Eiji Takahashi(NEC) |
| 幹事氏名（和） | 中山 裕貴(ボスコ・テクノロジーズ) / 内海 哲哉(富士通) |
| 幹事氏名（英） | Hiroki Nakayama(Bosco) / Tetsuya Uchiumi(Fujitsu) |
| 幹事補佐氏名（和） | 加藤 能史(NTT) |
| 幹事補佐氏名（英） | Yoshifumi Kato(NTT) |
| 講演論文情報詳細 | |
| 申込み研究会 | Technical Committee on Information and Communication Management |
|---|---|
| 本文の言語 | ENG |
| タイトル（和） | |
| サブタイトル（和） | |
| タイトル（英） | [Invited Talk] Fuzzy Logic-based Client Selection for Federated Learning in Vehicular IoT |
| サブタイトル（和） | |
| キーワード(1)（和/英） | / Federated learningClient selectionFuzzy logicVehicular IoT |
| 第 1 著者 氏名（和/英） | 策力 木格 / Celimuge Wu |
| 第 1 著者 所属（和/英） | 電気通信大学(略称：電通大) The University of Electro-Communications(略称：UEC) |
| 発表年月日 | 2022-03-04 |
| 資料番号 | ICM2021-50 |
| 巻番号（vol） | vol.121 |
| 号番号（no） | ICM-399 |
| ページ範囲 | pp.47-47(ICM), |
| ページ数 | 1 |
| 発行日 | 2022-02-24 (ICM) |