CSAHFL:Clustered Semi-Asynchronous Hierarchical Federated Learning for Dual-layer Non-IID in Heterogeneous Edge Computing Networks

Li, Aijing; Du, Junping; Liu, Dandan; Shao, Yingxia; Zhao, Tong; Ye, Guanhua

doi:10.24963/ijcai.2025/621

CSAHFL:Clustered Semi-Asynchronous Hierarchical Federated Learning for Dual-layer Non-IID in Heterogeneous Edge Computing Networks

Aijing Li, Junping Du, Dandan Liu, Yingxia Shao, Tong Zhao, Guanhua Ye

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 5580-5588.

https://doi.org/10.24963/ijcai.2025/621

Keywords

Machine Learning: ML: Clustering
Machine Learning: ML: Federated learning

Abstract

Federated Learning (FL) enables collaborative model training across distributed devices without sharing raw data. Hierarchical Federated Learning (HFL) is a new paradigm of FL that leverages the Edge Servers (ESs) layer as an intermediary to perform partial local model aggregation in proximity, reducing core network transmission overhead. However, HFL faces new challenges: (1) The two-stage aggregation process between client-edge and edge-cloud results in a dual-layer non-IID issue, which may significantly compromise model training accuracy. (2) The heterogeneity and mobility of clients further impact model training efficiency. To address these challenges, we propose a novel Clustered Semi-Asynchronous Hierarchical Federated Learning (CSAHFL) framework that integrates adaptive semi-asynchronous intra-cluster aggregation at client-edge layer and dynamic distribution-aware inter-cluster aggregation at edge-cloud layer, collaboratively enhancing model performance and scalability in heterogeneous and mobile environments. We conducte experiments under varying degrees of dual-layer non-IID in both static and high-mobility scenarios. The results demonstrate significant advantages of CSAHFL over representative state-of-the-art methods.

Aijing Li, Junping Du, Dandan Liu, Yingxia Shao, Tong Zhao, and Guanhua Ye. 2025. CSAHFL:Clustered Semi-Asynchronous Hierarchical Federated Learning for Dual-layer Non-IID in Heterogeneous Edge Computing Networks. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 5580–5588. https://doi.org/10.24963/ijcai.2025/621

@inproceedings{ijcai2025p621,
  title     = {CSAHFL:Clustered Semi-Asynchronous Hierarchical Federated Learning for Dual-layer Non-IID in Heterogeneous Edge Computing Networks},
  author    = {Li, Aijing and Du, Junping and Liu, Dandan and Shao, Yingxia and Zhao, Tong and Ye, Guanhua},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {5580--5588},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/621},
  url       = {https://doi.org/10.24963/ijcai.2025/621},
}

TY  - CPAPER
TI  - CSAHFL:Clustered Semi-Asynchronous Hierarchical Federated Learning for Dual-layer Non-IID in Heterogeneous Edge Computing Networks
AU  - Li, Aijing
AU  - Du, Junping
AU  - Liu, Dandan
AU  - Shao, Yingxia
AU  - Zhao, Tong
AU  - Ye, Guanhua
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 5580
EP  - 5588
DO  - 10.24963/ijcai.2025/621
UR  - https://doi.org/10.24963/ijcai.2025/621
ER  -