Clustering-Based User Selection in Federated Learning: Metadata Exploitation for 3GPP Networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911386369523712 |
|---|---|
| author | Zheng, Ce Ma, Shiyao Zhang, Ke Sun, Chen Zhang, Wenqi |
| author_facet | Zheng, Ce Ma, Shiyao Zhang, Ke Sun, Chen Zhang, Wenqi |
| contents | Federated learning (FL) enables collaborative model training without sharing raw user data, but conventional simulations often rely on unrealistic data partitioning and current user selection methods ignore data correlation among users. To address these challenges, this paper proposes a metadatadriven FL framework. We first introduce a novel data partition model based on a homogeneous Poisson point process (HPPP), capturing both heterogeneity in data quantity and natural overlap among user datasets. Building on this model, we develop a clustering-based user selection strategy that leverages metadata, such as user location, to reduce data correlation and enhance label diversity across training rounds. Extensive experiments on FMNIST and CIFAR-10 demonstrate that the proposed framework improves model performance, stability, and convergence in non-IID scenarios, while maintaining comparable performance under IID settings. Furthermore, the method shows pronounced advantages when the number of selected users per round is small. These findings highlight the framework's potential for enhancing FL performance in realistic deployments and guiding future standardization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_10013 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Clustering-Based User Selection in Federated Learning: Metadata Exploitation for 3GPP Networks Zheng, Ce Ma, Shiyao Zhang, Ke Sun, Chen Zhang, Wenqi Signal Processing Distributed, Parallel, and Cluster Computing Federated learning (FL) enables collaborative model training without sharing raw user data, but conventional simulations often rely on unrealistic data partitioning and current user selection methods ignore data correlation among users. To address these challenges, this paper proposes a metadatadriven FL framework. We first introduce a novel data partition model based on a homogeneous Poisson point process (HPPP), capturing both heterogeneity in data quantity and natural overlap among user datasets. Building on this model, we develop a clustering-based user selection strategy that leverages metadata, such as user location, to reduce data correlation and enhance label diversity across training rounds. Extensive experiments on FMNIST and CIFAR-10 demonstrate that the proposed framework improves model performance, stability, and convergence in non-IID scenarios, while maintaining comparable performance under IID settings. Furthermore, the method shows pronounced advantages when the number of selected users per round is small. These findings highlight the framework's potential for enhancing FL performance in realistic deployments and guiding future standardization. |
| title | Clustering-Based User Selection in Federated Learning: Metadata Exploitation for 3GPP Networks |
| topic | Signal Processing Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2601.10013 |