Applicaiton Required

H11-M26_基於用戶回饋資訊之分散式動態訓練策略

Abstract

Federated learning provides a decentralized learning without data exchange. Among them, the Federated Average (FedAVG) framework is the most likely to be implemented in real world application due to its low communication overhead. However, this architecture can easily affect the efficiency of global model convergence when there are differences data distribution in individual user. Therefore, in this paper, we propose an aggregation strategy called significant Weighted feature aggregation method, in which the features with large variation are appropriately weighted at the server side to improve the model convergence speed even in not identically and independently distributed (non-iid) environments. As shown in our experiments, our approach had over 10% of improvements compared to the FedAVG.

Keywords

deep learning, distribution system, federated learning

Data and Resources

Additional Info

Field Value
Author 楊惟中
Maintainer 羅梅爾
Last Updated October 4, 2023, 09:57 (CST)
Created July 11, 2023, 11:04 (CST)

推薦資料集:


  • 台南賽鴿笭統計資料

    Payment instrument Free
    Update frequency Irregular
    臺南市「新營鹽水學甲放粉鳥(紅腳)笭」市定民俗活動名冊d
  • 110年臺南市公告土地現值表

    Payment instrument Free
    Update frequency Irregular
    110年-臺南市公告土地現值表
  • 新北市轄內固定污染源空氣污染物監測數據-即時

    Payment instrument Free
    Update frequency Irregular
    針對固定污染源空氣污染物連續自動監測設施(CEMS)監測數據-即時
  • Applicaiton Required

    2016年福爾摩沙衛星二號 L4 宜蘭

    Payment instrument Free
    Update frequency Irregular
    此資料集為非公開資料,需由 TASA 進行資料審核。 欲申請者,請進入資料集後點選右上方「申請」填寫申請單;申請前請先登入系統。 若尚無平台帳號,請至 https://scidm.nchc.org.tw/user/register 進行註冊
  • 警察機關查獲毒品嫌疑犯人數─按年齡別分

    Payment instrument Free
    Update frequency Irregular
    警察機關查獲毒品嫌疑犯人數─按年齡別分(資料起始時間:89年01月)