Distributed Split Learning for Map-Based Signal Strength Prediction Empowered by Deep Vision Transformer

This article focuses on predicting the received signal strength (RSS) of mobile users, which is a fundamental problem for improving the coverage of cellular networks. Traditional methods for RSS prediction are based on ray tracing or stochastic radio propagation models. However, the former requires detailed environmental information that may not be practically available, while the latter cannot use the environmental data to its full potential and is not accurate enough. To address these issues, we design a practical RSS prediction system utilizing the trajectory information of users and satellite maps around base stations without sharing raw data. Specifically, we propose a map-based deep neural network (DNN) for the RSS prediction, empowered by the deep vision transformer (DeepVIT). Furthermore, to avoid sharing raw data, a novel split learning (SL) framework is developed. It splits the map-based DNN into two parts, which are deployed on the server and the user sides, respectively. The proposed models are evaluated by eight real-world data sets provided by an Australian Telecom operator, including 307,500 data samples. Simulation results show that in terms of prediction accuracy, the proposed map-based DNN significantly outperforms the 3GPP Urban Macro model and the long short-term memory method in centralized scenarios, while its SL variant outperforms the sequential SL and federated learning (FL) approaches in distributed scenarios. In addition, the communication overhead and the on-device computational burden of the proposed SL model are much lower than that of the FL approach.

• Publication year

  2024

• Venue

  IEEE Transactions on Vehicular Technology

• Publication date

  2024-02-01

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1109/TVT.2023.3320643
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Secure Split Learning against Property Inference, Data Reconstruction, and Feature Space Hijacking Attacks

  2023cited by this paper
• HiveMind: Towards Cellular Native Machine Learning Model Splitting

  2022cited by this paper
• Split Learning Over Wireless Networks: Parallel Design and Resource Management

  2022cited by this paper
• Feature Space Hijacking Attacks against Differentially Private Split Learning

  2022cited by this paper
• SplitGuard: Detecting and Mitigating Training-Hijacking Attacks in Split Learning

  2021cited by this paper
• Rethinking Spatial Dimensions of Vision Transformers

  2021cited by this paper
• Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

  2021cited by this paper
• DeepViT: Towards Deeper Vision Transformer

  2021influential reference
• Accuracy Versus Complexity for mmWave Ray-Tracing: A Full Stack Perspective

  2021cited by this paper
• Toward Environment-Aware 6G Communications via Channel Knowledge Map

  2021cited by this paper
• Distributed Signal Strength Prediction using Satellite Map empowered by Deep Vision Transformer

  2021influential reference
• PMF

  2020cited by this paper
• Model-Aided Deep Learning Method for Path Loss Prediction in Mobile Communication Systems at 2.6 GHz

  2020influential reference
• Communication-Efficient Multimodal Split Learning for mmWave Received Power Prediction

  2020cited by this paper
• Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training?

  2020cited by this paper
• Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

  2020cited by this paper
• Deep Learning-based Signal Strength Prediction Using Geographical Images and Expert Knowledge

  2020influential reference
• NoPeek: Information leakage reduction to share activations in distributed deep learning

  2020cited by this paper
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

  2020influential reference
• Unleashing the Tiger: Inference Attacks on Split Learning

  2020cited by this paper
• Federated Learning: Challenges, Methods, and Future Directions

  2019cited by this paper
• Federated learning of predictive models from federated Electronic Health Records

  2018cited by this paper
• Data augmentation for improving deep learning in image classification problem

  2018cited by this paper
• Federated Learning with Non-IID Data

  2018cited by this paper
• Split learning for health: Distributed deep learning without sharing raw patient data

  2018cited by this paper
• Human Activity Recognition Using Federated Learning

  2018cited by this paper
• Attention is All you Need

  2017cited by this paper
• Deep Learning

  2016cited by this paper
• Communication-Efficient Learning of Deep Networks from Decentralized Data

  2016cited by this paper
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence

  2016cited by this paper
• Rethinking cellular network planning and optimization

  2016cited by this paper
• Ray Tracing for Radio Propagation Modeling: Principles and Applications

  2015cited by this paper
• How to Construct Deep Recurrent Neural Networks

  2013cited by this paper
• Seamless Dual-Link Handover Scheme in Broadband Wireless Communication Systems for High-Speed Rail

  2012cited by this paper
• Learning to Forget: Continual Prediction with LSTM

  2000cited by this paper

• Geographic Knowledge-Driven Transfer Learning for Enhanced Received Signal Strength Prediction

  2026cites this paper
• Reconstructing Spatial Localization Error Maps via Physics-Informed Tensor Completion for Passive Sensor Systems

  2026cites this paper
• A Recent Survey on Radio Map Estimation Methods for Wireless Networks

  2025cites this paper
• Spatial Transformers for Radio Map Estimation

  2024cites this paper
• RSRP Prediction In Low Altitude by Deep Learning-Based Method and Geographic Information

  2024cites this paper