Secure aggregation for semi-decentralized federated learning under heterogeneous data

Semi-decentralized federated learning has gained attention for combining the advantages of centralized and decentralized approaches, thereby enhancing system scalability and flexibility. However, in the open heterogeneous federated learning architecture, the existence of semi-honest participants and...

Full description

Saved in:
Bibliographic Details
Main Authors: HUANG Mei, WANG Lingling, ZHANG Zhengyin, LIU Yufei, SUN Yitong
Format: Article
Language:English
Published: POSTS&TELECOM PRESS Co., LTD 2025-06-01
Series:网络与信息安全学报
Subjects:
Online Access:http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2025029
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849424368112762880
author HUANG Mei
WANG Lingling
ZHANG Zhengyin
LIU Yufei
SUN Yitong
author_facet HUANG Mei
WANG Lingling
ZHANG Zhengyin
LIU Yufei
SUN Yitong
author_sort HUANG Mei
collection DOAJ
description Semi-decentralized federated learning has gained attention for combining the advantages of centralized and decentralized approaches, thereby enhancing system scalability and flexibility. However, in the open heterogeneous federated learning architecture, the existence of semi-honest participants and heterogeneous data has aggravated the problems of node privacy leakage and difficult model convergence during model aggregation. The differences between local models have increased with the degree of local data heterogeneity, which has further slowed down the global model’ convergence and reduced its accuracy. Additionally, the complex network topology among nodes has heightened the risk of local data privacy leakage, making it difficult to ensure local data privacy protection. To tackle these issues, a secure aggregation scheme for heterogeneous data under a semi-distributed federated learning architecture was designed. This scheme aimed to enhance the global model’s convergence performance while safeguarding node privacy. A random masking mechanism was developed based on the alternating direction multiplier method. This mechanism strengthened local data privacy protection and prevented access to individual node models. Moreover, a double-weighted aggregation strategy was proposed. In this strategy, intra-cluster aggregation weights for nodes were determined based on the loss of the global model on different node samples, and global aggregation weights for different clusters were established according to their contribution to the global model. Extensive experiments were carried out on three public standard datasets. The results demonstrate that, compared with advanced schemes, the proposed method improves model convergence speed and accuracy in the context of heterogeneous data.
format Article
id doaj-art-ee9ff00efc864a72907ba1d3257f249c
institution Kabale University
issn 2096-109X
language English
publishDate 2025-06-01
publisher POSTS&TELECOM PRESS Co., LTD
record_format Article
series 网络与信息安全学报
spelling doaj-art-ee9ff00efc864a72907ba1d3257f249c2025-08-20T03:30:13ZengPOSTS&TELECOM PRESS Co., LTD网络与信息安全学报2096-109X2025-06-0111175189113007813Secure aggregation for semi-decentralized federated learning under heterogeneous dataHUANG MeiWANG LinglingZHANG ZhengyinLIU YufeiSUN YitongSemi-decentralized federated learning has gained attention for combining the advantages of centralized and decentralized approaches, thereby enhancing system scalability and flexibility. However, in the open heterogeneous federated learning architecture, the existence of semi-honest participants and heterogeneous data has aggravated the problems of node privacy leakage and difficult model convergence during model aggregation. The differences between local models have increased with the degree of local data heterogeneity, which has further slowed down the global model’ convergence and reduced its accuracy. Additionally, the complex network topology among nodes has heightened the risk of local data privacy leakage, making it difficult to ensure local data privacy protection. To tackle these issues, a secure aggregation scheme for heterogeneous data under a semi-distributed federated learning architecture was designed. This scheme aimed to enhance the global model’s convergence performance while safeguarding node privacy. A random masking mechanism was developed based on the alternating direction multiplier method. This mechanism strengthened local data privacy protection and prevented access to individual node models. Moreover, a double-weighted aggregation strategy was proposed. In this strategy, intra-cluster aggregation weights for nodes were determined based on the loss of the global model on different node samples, and global aggregation weights for different clusters were established according to their contribution to the global model. Extensive experiments were carried out on three public standard datasets. The results demonstrate that, compared with advanced schemes, the proposed method improves model convergence speed and accuracy in the context of heterogeneous data.http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2025029semi-decentralized federated learningprivacy protectionweighted aggregationheterogeneous data
spellingShingle HUANG Mei
WANG Lingling
ZHANG Zhengyin
LIU Yufei
SUN Yitong
Secure aggregation for semi-decentralized federated learning under heterogeneous data
网络与信息安全学报
semi-decentralized federated learning
privacy protection
weighted aggregation
heterogeneous data
title Secure aggregation for semi-decentralized federated learning under heterogeneous data
title_full Secure aggregation for semi-decentralized federated learning under heterogeneous data
title_fullStr Secure aggregation for semi-decentralized federated learning under heterogeneous data
title_full_unstemmed Secure aggregation for semi-decentralized federated learning under heterogeneous data
title_short Secure aggregation for semi-decentralized federated learning under heterogeneous data
title_sort secure aggregation for semi decentralized federated learning under heterogeneous data
topic semi-decentralized federated learning
privacy protection
weighted aggregation
heterogeneous data
url http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2025029
work_keys_str_mv AT huangmei secureaggregationforsemidecentralizedfederatedlearningunderheterogeneousdata
AT wanglingling secureaggregationforsemidecentralizedfederatedlearningunderheterogeneousdata
AT zhangzhengyin secureaggregationforsemidecentralizedfederatedlearningunderheterogeneousdata
AT liuyufei secureaggregationforsemidecentralizedfederatedlearningunderheterogeneousdata
AT sunyitong secureaggregationforsemidecentralizedfederatedlearningunderheterogeneousdata