Skip to content
Preprint

Cross-Site Transfer and Spatial Forgetting in OTA-Trained Neural Receivers

Oct 2026 · 0 citations · 14 references
Engineering

Abstract

Most published neural-receiver studies train on synthetic channel models, although real over-the-air measurements can improve performance. We examine how much of this benefit transfers from other sites to a distinctly different deployment site and what adaptation to that site costs elsewhere. The study uses a dataset from a 5.88 GHz measurement campaign covering eight sites and four environment types. An industrial site measured entirely from a vehicle is withheld as a deliberate transfer stress test. One receiver architecture is trained under four regimes: simulation alone; seven other sites; all sites jointly; and other-site training followed by deployment-site finetuning. The last two use identical measurements through different optimization protocols. Across five independently trained seeds, sensitivity gains are evaluated at uncoded bit error rate (BER) targets of $10^{-1}$ and $10^{-2}$, representative of moderate- and higher-rate coded links, respectively. On the deployment site, training with other-site data rather than simulation improves sensitivity by 0.3 dB at $10^{-1}$ and 0.1 dB at $10^{-2}$. Adding deployment-site data contributes less than 0.1 dB at $10^{-1}$; at $10^{-2}$, total gains over simulation reach 0.4 dB with joint training and 0.6 dB with finetuning. Joint training shows no measurable aggregate loss on the other-site test set, whereas finetuning yields the larger deployment-site gain but reduces other-site sensitivity by about 0.1 dB at $10^{-2}$, indicating spatial forgetting.

View source

Similar papers

Preprint Sep 2026

On the Impact of Site-Specific Training for a Real-World 5G NR System

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, mod...

Reinhard Wiesmayr, Nuri Berke Baytekin, Chris Dick et al. · 1 citation
#small language model Open access Sep 2026

Reconstructing wireless signals for low altitude networks using small language models

In-Context Signal Completion (ICSC) is presented, demonstrating that small language models fine-tuned with Group Relative Policy Optimization and physics-informed rewards can reconstruct RSSI across sequential extrapolation and spatial interpolation tasks.

Xin Li, Ran Liu, Chau Yuen · 0 citations
Sep 2026

An Empirical Study of Domain Generalization and Test-Time Adaptation on CSI-Bench

The CSI-Bench benchmark reports its Human Activity Recognition (HAR) out-of-distribution (OOD) results only in a multi-task joint regime and evaluates no domain generalization (DG) or test-time adaptation (TTA) method. We report a controlled study of six DG and three TTA methods on CSI-Bench HAR under one shared protoc...

Yi Liu, Zheng-Guo Sheng · 0 citations
Open access Sep 2026

Prediction of channel propagation impairments in LEO satellite networks using machine learning

The proposed framework maintains consistent prediction performance across all untrained European cities, while the uncertainty estimation mechanism provides calibrated confidence measures that may support operational decision-making, making the proposed framework a promising approach for large-scale predictive link ada...

Salma A. El-Sayed, Micheal Ibrahim, Hadia M. Elhennawy et al. · 0 citations
Preprint Oct 2026

Radar-Only Long-Term Beam Prediction in mmWave Vehicular Networks: An Empirical Study of Doppler Input and Cross-Modal Distillation

For this predictor family and the full training set, the measurable gain at the link comes from Doppler-resolved radar content; no tested route for transferring training-only visual information adds a resolved gain.

Jeongwan Kang, Miguel Bordallo López, N. Nguyen et al. · 1 citation
#machine learning Preprint Oct 2026

DBCM: Dual-Branch Calibration Module for Test-Time Adaptation in Time Series Forecasting

Non-stationarity induces test-time distribution shifts in time series forecasting (TSF), resulting in forecast residuals between predictions and the corresponding ground truth. Recent works on test-time adaptation for TSF address this by introducing lightweight calibration modules around frozen forecasters, updated usi...

Jae-Hoon Jeon, Kunwoo Kang, Sang Yup Lee et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.