When Does a Neural Receiver Help? Calibration-Drift Benchmarking and Detect-and-Rollback for 5G/6G NR
arXiv:2605.261570.2
AI Analysis
For 5G/6G system designers, it identifies a critical failure mode of neural receivers and offers a practical mitigation strategy.
The paper benchmarks neural receiver (DeepRx) performance under calibration drift in 5G/6G NR, showing it outperforms MMSE in-distribution but degrades under drift, and proposes a detect-and-rollback mechanism to maintain reliability.
Convolutional neural receivers such as DeepRx outperform minimum mean-square error physical uplink shared channel detection on in distribution channel and waveform configurations, but their behavior under calibration drift when transmitter or channel parameters depart from the training envelope is poorly characterized.