文献类型：期刊文献

英文题名：FedBKT: Federated Learning with Model Heterogeneity via Bidirectional Knowledge Transfer with Mediator Model

作者：Min, Qi[1]; Wang, Hui[2,3]; Jia, Peng[1]; Qiu, Yuan[2,3]; Gu, Chunhua[1]; Ding, Weichao[1]

机构：[1] School of Information Science and Engineering, East China University of Science and Technology, Shanghai, 200237, China; [2] Shanghai Aerospace Electronic Technology Institute, Shanghai, 201109, China; [3] Shanghai Key Laboratory of Collaborative Computing in Spacial Heterogenous Networks [CCSN], Shanghai, 201109, China

年份：2025

卷号：15851 LNCS

起止页码：394

外文期刊名：Lecture Notes in Computer Science

收录：EI(收录号：20253118910906)

语种：英文

外文关键词：Data mining - Data privacy - Extraction - Information retrieval - Knowledge acquisition - Knowledge management

摘要：Federated learning (FL) enables the training of global models across devices without the need to access local data. However, the heterogeneity of models and data across devices poses significant challenges in aggregating and aligning global information. In existing FL methods, knowledge transfer between the server and clients mainly relies on soft labels, a method that is affected by heterogeneity and raises privacy and data collection concerns due to its dependence on additional datasets. This paper proposes a FL paradigm based on Bidirectional Knowledge Transfer, named FedBKT, which leverages a mediator model to collect global information from each client. To achieve this, we introduce a Knowledge extraction module. After aggregation on the server, knowledge is transferred from the mediator model to local models via the Knowledge Sharing module, facilitating efficient information extraction and sharing. Experimental results in heterogeneous scenarios show that FedBKT outperforms existing methods across multiple metrics and effectively mitigates the negative impact of heterogeneity on performance. ? The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.