On the Impact of Site-Specific Training for a Real-World 5G NR System
Abstract
Site-specific training can improve wireless receiver performance without increasing computational complexity. However, real-world results have so far focused on fully trainable neural receivers and single-layer transmissions. We study site-specific finetuning of three receiver architectures: fully trainable neural, model-driven neural, and model-based. We train and evaluate these receivers using new measurements from a standard-compliant 5G NR testbed at ETH Zurich with dual-layer uplink transmission, including measurement campaigns conducted more than six months apart. Our results show that site-specific finetuning (i) substantially improves fully trainable and model-driven neural receivers, while resulting in only marginal gains for the less tunable model-based receiver; (ii) enables a single neural receiver jointly finetuned for single- and dual-layer transmission to closely match receivers finetuned separately for each configuration; and (iii) remains effective across measurement campaigns separated by more than six months. We also investigate site-specific linear minimum mean-square error channel estimation using covariance matrices estimated from either synthetic channels or site-specific measurements. When combined with iterative detection and decoding, site-specific channel estimation achieves the lowest error rate observed in our datasets. Our finetuning code and measurement datasets are publicly available at https://github.com/IIP-Group/site_specific_training
Related
- Learning Changes the World and Then What Was Learned has Changed: Training and Deploying Neural Networks in the Control Loop
- AIPS: an automated interferential plasmonic system for on-site bioaerosol detection
- Weighting risk impact indicators in a food system: expert elicitation and analysis prior to inclusion in a multi-risk assessment
- Designing multi‐site studies for external validity: Site selection via synthetic purposive sampling
- Locality of Bernoulli Site Percolation on Transitive Graphs
BibTeX
@misc{wiesmayr2026impact,
title = {{On the Impact of Site-Specific Training for a Real-World 5G NR System}},
author = {Reinhard Wiesmayr and Nuri Berke Baytekin and Chris Dick and Christoph Studer},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.04004},
eprint = {2609.04004},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.04004},
}
RIS
TY - UNPB
TI - On the Impact of Site-Specific Training for a Real-World 5G NR System
AU - Reinhard Wiesmayr
AU - Nuri Berke Baytekin
AU - Chris Dick
AU - Christoph Studer
PY - 2026
DA - 2026/09/03
PB - arXiv
DO - 10.48550/arxiv.2609.04004
UR - https://arxiv.org/abs/2609.04004
AB - Site-specific training can improve wireless receiver performance without increasing computational complexity. However, real-world results have so far focused on fully trainable neural receivers and single-layer transmissions. We study site-specific finetuning of three receiver architectures: fully trainable neural, model-driven neural, and model-based. We train and evaluate these receivers using new measurements from a standard-compliant 5G NR testbed at ETH Zurich with dual-layer uplink transmission, including measurement campaigns conducted more than six months apart. Our results show that site-specific finetuning (i) substantially improves fully trainable and model-driven neural receivers, while resulting in only marginal gains for the less tunable model-based receiver; (ii) enables a single neural receiver jointly finetuned for single- and dual-layer transmission to closely match receivers finetuned separately for each configuration; and (iii) remains effective across measurement campaigns separated by more than six months. We also investigate site-specific linear minimum mean-square error channel estimation using covariance matrices estimated from either synthetic channels or site-specific measurements. When combined with iterative detection and decoding, site-specific channel estimation achieves the lowest error rate observed in our datasets. Our finetuning code and measurement datasets are publicly available at https://github.com/IIP-Group/site_specific_training
ER -