FedAux: An Efficient Framework for Hybrid Federated Learning

Hang Gu, Bin Guo, Jiangtao Wang, Wen Sun, Jiaqi Liu, Sicong Liu, Zhiwen Yu

科研成果: 书/报告/会议事项章节会议稿件同行评审

10 引用 (Scopus)

摘要

As an enabler of sixth-generation communication technology (6G), Federated Learning (FL) triggers a paradigm shift from "connected things"to "connected intelligence". FL implements on-device learning, where massive end devices jointly and locally train a model without private data leakage. However, FL suffers from problems of low accuracy and convergence rate when no data is shared to the central server and the data distribution is non-IID. In recent years, attempts have been made on hybrid FL, where very small amounts of data (e.g., less than 1%) is shared from the participants. With the opportunities brought by shared data, we notice that the server is capable of receiving the data in order to assist the FL process and mitigate the challenge of non-IID. Notably, existing hybrid FL only applies the model-level technologies belonging to the traditional FL and does not make full use of the characteristics of shared data to make targeted improvements. In this paper, we propose FedAux, a novel hybrid FL method at knowledge-level, which utilizes shared data to construct an auxiliary model and then transfer general knowledge to traditional aggregated model or client model for enhancing the accuracy of global model and speeding up the convergence of global model. We also propose two specific knowledge transfer strategies named c-transfer and i-transfer. We conduct extensive analysis and evaluation of our methods against the well-known FL methods, FedAvg and Hybrid-FL protocol. The results indicate that FedAux shows higher accuracy (10.89%) and faster convergence rate compared with other methods.

源语言英语
主期刊名ICC 2022 - IEEE International Conference on Communications
出版商Institute of Electrical and Electronics Engineers Inc.
195-200
页数6
ISBN(电子版)9781538683477
DOI
出版状态已出版 - 2022
活动2022 IEEE International Conference on Communications, ICC 2022 - Seoul, 韩国
期限: 16 5月 202220 5月 2022

出版系列

姓名IEEE International Conference on Communications
2022-May
ISSN(印刷版)1550-3607

会议

会议2022 IEEE International Conference on Communications, ICC 2022
国家/地区韩国
Seoul
时期16/05/2220/05/22

指纹

探究 'FedAux: An Efficient Framework for Hybrid Federated Learning' 的科研主题。它们共同构成独一无二的指纹。

引用此