Digital Self-Interference Cancellation for In-Band Full-Duplex Systems Based on Transformer Neural Operators
Abstract
Digital-domain self-interference cancellation is essential in in-band full-duplex radios after passive suppression and analog cancellation. It is particularly challenging when the desired signal is strong relative to the residual self-interference. In this regime, conventional iterative digital cancellers update their coefficients from desired-signal-contaminated received samples and may suffer substantial performance degradation. This paper reformulates digital-domain self-interference cancellation as an operator-learning problem. The proposed framework learns the temporal evolution of the residual self-interference channel from historical observations and uses the learned operator together with the known local transmit signal to reconstruct the current residual self-interference. A Transformer neural operator is used to realize this framework. The resulting method is trained in a desired-signal-free setting and then applied in the presence of a desired signal. A continuity-based analysis characterizes the sensitivity of the learned operator to the resulting input perturbation. Numerical experiments in static and time-varying channels, including time-varying SIR conditions, demonstrate stable cancellation performance over a wide range of interference levels. At 30 dB SIR, the proposed method improves the cancellation performance by 5--15 dB over the considered conventional methods.
Related
- Nonperturbative Chiral Anomaly Cancellation and Irrelevant Operators
- Cancellation of complex kernels and sharp critical lines and endpoint theory for the Forelli--Rudin operators I: the purely hypersingular case
- Context-Aware Detection of Content Evidencing Illegal or Predatory Fintech Lending Practices on Indonesian Digital Platforms Using Transformer-Based Language Models
- Digital Transformer for Fracture Classification: SYM-Fractron, a Physics-Driven Hybrid Binary–Symbolic Computing Ecosystem
- Classification of pairs of second-order Hamiltonian operators and hydrodynamic type systems in six components
BibTeX
@misc{su2026digital,
title = {{Digital Self-Interference Cancellation for In-Band Full-Duplex Systems Based on Transformer Neural Operators}},
author = {Zhijie Su and Shiquan Zhang and Qiaolin He},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.19490},
eprint = {2610.19490},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.19490},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Digital Self-Interference Cancellation for In-Band Full-Duplex Systems Based on Transformer Neural Operators
AU - Zhijie Su
AU - Shiquan Zhang
AU - Qiaolin He
PY - 2026
DA - 2026/10/14
PB - arXiv
DO - 10.48550/arxiv.2610.19490
UR - https://arxiv.org/abs/2610.19490
AB - Digital-domain self-interference cancellation is essential in in-band full-duplex radios after passive suppression and analog cancellation. It is particularly challenging when the desired signal is strong relative to the residual self-interference. In this regime, conventional iterative digital cancellers update their coefficients from desired-signal-contaminated received samples and may suffer substantial performance degradation. This paper reformulates digital-domain self-interference cancellation as an operator-learning problem. The proposed framework learns the temporal evolution of the residual self-interference channel from historical observations and uses the learned operator together with the known local transmit signal to reconstruct the current residual self-interference. A Transformer neural operator is used to realize this framework. The resulting method is trained in a desired-signal-free setting and then applied in the presence of a desired signal. A continuity-based analysis characterizes the sensitivity of the learned operator to the resulting input perturbation. Numerical experiments in static and time-varying channels, including time-varying SIR conditions, demonstrate stable cancellation performance over a wide range of interference levels. At 30 dB SIR, the proposed method improves the cancellation performance by 5--15 dB over the considered conventional methods.
ER -