EPFL-REMNet: Efficient Personalized Federated Digital Twin Towards 6G Heterogeneous Radio Environment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Peide, Cao, Liu, Zhang, Lyutianyang, Wei, Dongyu, Hu, Ye, Xie, Qipeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909897544695808
author Li, Peide
Cao, Liu
Zhang, Lyutianyang
Wei, Dongyu
Hu, Ye
Xie, Qipeng
author_facet Li, Peide
Cao, Liu
Zhang, Lyutianyang
Wei, Dongyu
Hu, Ye
Xie, Qipeng
contents Radio Environment Map (REM) is transitioning from 5G homogeneous environments to B5G/6G heterogeneous landscapes. However, standard Federated Learning (FL), a natural fit for this distributed task, struggles with performance degradation in accuracy and communication efficiency under the non-independent and identically distributed (Non-IID) data conditions inherent to these new environments. This paper proposes EPFL-REMNet, an efficient personalized federated framework for constructing a high-fidelity digital twin of the 6G heterogeneous radio environment. The proposed EPFL-REMNet employs a"shared backbone + lightweight personalized head" model, where only the compressed shared backbone is transmitted between the server and clients, while each client's personalized head is maintained locally. We tested EPFL-REMNet by constructing three distinct Non-IID scenarios (light, medium, and heavy) based on radio environment complexity, with data geographically partitioned across 90 clients. Experimental results demonstrate that EPFL-REMNet simultaneously achieves higher digital twin fidelity (accuracy) and lower uplink overhead across all Non-IID settings compared to standard FedAvg and recent state-of-the-art methods. Particularly, it significantly reduces performance disparities across datasets and improves local map accuracy for long-tail clients, enhancing the overall integrity of digital twin.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05238
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EPFL-REMNet: Efficient Personalized Federated Digital Twin Towards 6G Heterogeneous Radio Environment
Li, Peide
Cao, Liu
Zhang, Lyutianyang
Wei, Dongyu
Hu, Ye
Xie, Qipeng
Networking and Internet Architecture
68T05, 90C26, 68M10
I.2.11; C.2.1; C.4; G.3
Radio Environment Map (REM) is transitioning from 5G homogeneous environments to B5G/6G heterogeneous landscapes. However, standard Federated Learning (FL), a natural fit for this distributed task, struggles with performance degradation in accuracy and communication efficiency under the non-independent and identically distributed (Non-IID) data conditions inherent to these new environments. This paper proposes EPFL-REMNet, an efficient personalized federated framework for constructing a high-fidelity digital twin of the 6G heterogeneous radio environment. The proposed EPFL-REMNet employs a"shared backbone + lightweight personalized head" model, where only the compressed shared backbone is transmitted between the server and clients, while each client's personalized head is maintained locally. We tested EPFL-REMNet by constructing three distinct Non-IID scenarios (light, medium, and heavy) based on radio environment complexity, with data geographically partitioned across 90 clients. Experimental results demonstrate that EPFL-REMNet simultaneously achieves higher digital twin fidelity (accuracy) and lower uplink overhead across all Non-IID settings compared to standard FedAvg and recent state-of-the-art methods. Particularly, it significantly reduces performance disparities across datasets and improves local map accuracy for long-tail clients, enhancing the overall integrity of digital twin.
title EPFL-REMNet: Efficient Personalized Federated Digital Twin Towards 6G Heterogeneous Radio Environment
topic Networking and Internet Architecture
68T05, 90C26, 68M10
I.2.11; C.2.1; C.4; G.3
url https://arxiv.org/abs/2511.05238