Selective Interference Suppression of Siamese-Net in Heterogeneous Interference Channels
Abstract
We study an end-to-end learnt short-block codes for a N-user real Gaussian interference channel with heterogeneous pairwise interference strengths, while keeping single-user decoding at every receiver. In this paper, we study the case wherein only a few dominant interferers exist and investigate whether Siamese-style coupled training can adapt selectively to encode (\& decode) to ensure optimal performance corresponding to best tradeoff between orthogonality and coding gain or it enforces unnecessary global orthogonality oblivious of the reality. Our work focuses on a 4-user unequal-interference configuration with one dominant pair (1,2) (of strength Λ) and a weak pair (with weak background coupling (λ)), through which we demonstrate a selective interference suppression phenomenon where the learned codebooks become near-orthogonal primarily for the dominant pair, while weakly coupled pairs retain alignment needed for coding gain. We quantify this behaviour using latent-space cross-user similarity statistics (worst-case coherence measure, average similarity measure, etc) and connect these geometric signatures to the observed BLER robustness under unequal interference. It seems that the SiameseNet selectively suppresses the interferences from various interferring user pairs to yield optimal tradeoff between coding gain and BLER dictated by orthogonality.
Related
- Leveraging Slowly Time-Varying AP-AP Channels for Interference Mitigation in Dynamic TDD
- Capacity Bounds for Optical Interference Channels Subject to Average Power Constraints
- Selective Randomization Inference for Interference
- Constrained Capacity for Faster-than-Nyquist Signaling in Frequency-Selective Fading Channels
- Joint Random Access and Localization in Cell-Free User-Centric Networks with Frequency-Selective Fading Channels
BibTeX
@misc{sinha2026selective,
title = {{Selective Interference Suppression of Siamese-Net in Heterogeneous Interference Channels}},
author = {Arkadeep Sinha and Shubham Paul and R. Manivasakan and Nambi Seshadri and R. David Koilpillai},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2608.27635},
eprint = {2608.27635},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.27635},
}
RIS
TY - UNPB
TI - Selective Interference Suppression of Siamese-Net in Heterogeneous Interference Channels
AU - Arkadeep Sinha
AU - Shubham Paul
AU - R. Manivasakan
AU - Nambi Seshadri
AU - R. David Koilpillai
PY - 2026
DA - 2026/09/18
PB - arXiv
DO - 10.48550/arxiv.2608.27635
UR - https://arxiv.org/abs/2608.27635
AB - We study an end-to-end learnt short-block codes for a N-user real Gaussian interference channel with heterogeneous pairwise interference strengths, while keeping single-user decoding at every receiver. In this paper, we study the case wherein only a few dominant interferers exist and investigate whether Siamese-style coupled training can adapt selectively to encode (\& decode) to ensure optimal performance corresponding to best tradeoff between orthogonality and coding gain or it enforces unnecessary global orthogonality oblivious of the reality. Our work focuses on a 4-user unequal-interference configuration with one dominant pair (1,2) (of strength Λ) and a weak pair (with weak background coupling (λ)), through which we demonstrate a selective interference suppression phenomenon where the learned codebooks become near-orthogonal primarily for the dominant pair, while weakly coupled pairs retain alignment needed for coding gain. We quantify this behaviour using latent-space cross-user similarity statistics (worst-case coherence measure, average similarity measure, etc) and connect these geometric signatures to the observed BLER robustness under unequal interference. It seems that the SiameseNet selectively suppresses the interferences from various interferring user pairs to yield optimal tradeoff between coding gain and BLER dictated by orthogonality.
ER -