Research Briefing
cs.IT 2605.29995v1 worth_reading

Low-Overhead Receiver Design for Data-Dependent Superimposed Training via Deep Learning

Xinjie Li, Xingyu Zhou, Jing Zhang, Chao-Kai Wen, Xiao Li, Shi Jin

Published 2026-05-28 14:26:16 相关性 1.0000 价值 0.7400 cs.IT eess.SP
arXiv PDF HTML

摘要

选中正文可添加批注

Superimposed pilot (SIP) transmission improves spectral efficiency by eliminating the dedicated pilot overhead required in orthogonal pilot (OP)-based schemes. However, SIP suffers from severe pilot-data coupling, which leads to a critical performance-complexity bottleneck at the receiver. To address this issue, this paper proposes a low-overhead transmission framework that revitalizes data-dependent superimposed training (DDST) with enhanced interference mitigation strategies. First, for quasi-static block-fading channels, an enhanced DDST receiver is developed to achieve non-iterative pilot-data decoupling by exploiting data-dependent algebraic structures. Second, to overcome the sensitivity of conventional DDST to channel variations and symbol misidentification in fast time-varying environments, a mix transmission scheme is developed. By strategically applying DDST to a subset of resource elements, the proposed scheme combines the interference-free transmission property of OP with the zero-pilot-overhead advantage of SIP, thereby improving demapping reliability and interference suppression. Furthermore, under the proposed mix scheme, a Vision Transformer-based neural receiver is designed to capture the orthogonal structure between pilots and perturbation-bearing data, as well as the underlying channel correlations, thereby relaxing the stringent quasi-static assumption required for interference disentanglement. Simulation results demonstrate that the proposed framework achieves significant performance gains in the low-to-medium SNR regime under time-varying channels while providing superior computational efficiency compared with state-of-the-art SIP receivers.

相关性判断

high
相关方向
wireless_communications channel_estimation receiver_design spectral_efficiency
判断依据

The paper is squarely in cs.IT/eess.SP and addresses superimposed pilot transmission, channel estimation, receiver design, and spectral-efficiency tradeoffs in MIMO-OFDM wireless communication, which are directly relevant to communications and information-theoretic receiver design.

价值判断

High relevance to cs.IT wireless receiver design, with a concrete low-overhead DDST/SIP framework for pilot-data decoupling and time-varying MIMO-OFDM channels. Structure analysis indicates multiple technical components, including algebraic non-iterative decoupling, mix resource-element transmission, and a ViT-based receiver evaluated under CDL-C channels. Claims suggest practical value through low-to-medium SNR gains and lower complexity versus prior SIP receivers, but evidence appears simulation-based.

核心问题与主要方法

核心问题

receiver design for pilot-data-coupled superimposed transmission with high spectral efficiency and low complexity

场景：coded MIMO-OFDM with DDST/SIP-style superimposed training under block-fading and time-varying channels

主要方法

DDST transmitter-side perturbation creates an algebraic orthogonality structure that suppresses data interference on pilot components under quasi-static channels. LMMSE channel estimation treats LS DDST estimates as noisy channel observations and uses spatial channel correlation through a Wiener-Hopf-style estimator. Hybrid CNN-LSTM denoising maps distorted initial data estimates to bit-level LLRs, exploiting periodic perturbation similarity and temporal correlations. Mixed transmission allocates only a subset of REs to DDST and leaves the rest as pure data, trading pilot-structure density against perturbation-free demapping reliability. The ViT encoder processes LS/despreading-derived patches with multi-head self-attention to learn latent orthogonal and channel-correlation structure under time variation. A CNN decoder performs local feature fusion and interpolation from DDST subcarriers to full channel estimates, while separate detection subnetworks handle DDST REs and pure data REs.

关键贡献与后续阅读

关键贡献

Develops an enhanced DDST receiver for coded MIMO-OFDM under block-fading channels using LMMSE channel estimation and a CNN-LSTM denoising detector that outputs LLRs rather than hard symbol decisions. Introduces a mixed DDST/pure-data transmission frame for time-varying channels, targeting the specific failure mode where Doppler variation destroys DDST orthogonality and worsens symbol misidentification. Designs a ViT-based channel estimation network with LS/despreading preprocessing, self-attention encoder, and CNN decoder to exploit pilot-data structure and channel correlations under time-varying MIMO-OFDM conditions. Uses separate detection subnetworks for DDST REs and pure data REs, reflecting the different residual-interference structures in perturbation-bearing and perturbation-free observations. Provides simulation evidence under CDL-C MIMO-OFDM channels that the mix receiver can improve NMSE, BLER/throughput, and runtime tradeoffs compared with OP and iterative SIP baselines.

研究启发

How strong are the SIP baselines relative to the latest neural or model-driven SIP receivers beyond the cited iterative JCDD-style receiver? Are the reported latency measurements hardware-specific, and do they include neural-network execution, channel decoding, and data movement overheads? How sensitive is the mixed allocation ratio r to channel delay spread, mobility, modulation order, and LDPC code rate outside the tested configurations? Can the ViT/CNN receiver generalize across broader CDL profiles, antenna configurations, and power allocation factors without retraining?

限制与不确定性

Novelty and importance depend on comparison strength against state-of-the-art SIP/neural receivers, which cannot be verified from the provided structure alone. Deep-learning receiver gains may be sensitive to channel/model mismatch and training setup. The work appears engineering-heavy rather than foundational information theory, so urgency is below must-read without stronger evidence of broad impact.

原文信息

正文记录 1
参考文献 40
最近更新 2026-05-30 13:21
查看正文预览 
Abstract

Content selection saved. Describe the issue below:

Low-Overhead Receiver Design for Data-Dependent Superimposed Training via Deep Learning

Superimposed pilot (SIP) transmission improves spectral efficiency by eliminating the dedicated pilot overhead required in orthogonal pilot (OP)-based schemes. However, SIP suffers from severe pilot-data coupling, which leads to a critical performance-complexity bottleneck at the receiver. To address this issue, this paper proposes a low-overhead transmission framework that revitalizes data-dependent superimposed training (DDST) with enhanced interference mitigation strategies. First, for quasi-static block-fading channels, an enhanced DDST receiver is developed to achieve non-iterative pilot-data decoupling by exploiting data-dependent algebraic structures. Second, to overcome the sensitivity of conventional DDST to channel variations and symbol misidentification in fast time-varying environments, a mix transmission scheme is developed. By strategically applying DDST to a subset of resource elements, the proposed scheme combines the interference-free transmission property of OP with the zero-pilot-overhead advantage of SIP, thereby
查看参考文献
  1. [1] T. L. Marzetta, “Noncooperative cellular wireless with unlimited numbers of base station antennas,” IEEE Trans. Wireless Commun. , vol. 9, no. 11, pp. 3590–3600, Nov. 2010.
  2. [2] X. Zhou, L. Liang, J. Zhang, P. Jiang, Y. Li, and S. Jin, “Generative diffusion models for high dimensional channel estimation,” IEEE Trans. Wireless Commun. , vol. 24, no. 7, pp. 5840–5854, Jul. 2025.
  3. [3] S. Trushkov, V. Kuptsov, O. Shmonin, K. Ponur, G. Serebryakov, and A. Blagodarnyi, “Pilot overhead reduction for antenna ports in MIMO OFDM systems using high-resolution map,” in Proc. IEEE Int. Black Sea Conf. Commun. Netw. (BlackSeaCom) , Tbilisi, Georgia, Jun. 2024, pp. 66–71.
  4. [4] 3GPP, “NR; Physical channels and modulation,” 3GPP TS 38.211, Tech. Rep., 2023.
  5. [5] M. Xie, X. Yu, K. Wang, J. Zhang, X. Dang, and C. Yuen, “Superimposed pilots for cell-free massive MIMO over spatial-correlated Rician fading channels,” IEEE Trans. Wireless Commun. , vol. 23, no. 12, pp. 19 537–19 552, Dec. 2024.
  6. [6] F. Ait Aoudia and J. Hoydis, “End-to-end learning for OFDM: From neural receivers to pilotless communication,” IEEE Trans. Wireless Commun. , vol. 21, no. 2, pp. 1049–1063, Feb. 2022.
  7. [7] H. Xiao et al. , “Interference cancellation based neural receiver for superimposed pilot in multi-layer transmission,” China Commun. , vol. 22, no. 1, pp. 75–88, Jan. 2025.
  8. [8] X. Zhou et al. , “Conditional diffusion model-enabled scenario-specific neural receivers for superimposed pilot schemes,” arXiv preprint arXiv:2511.01173 , 2025.
  9. [9] J. Ma, C. Liang, C. Xu, and L. Ping, “On orthogonal and superimposed pilot schemes in massive MIMO NOMA systems,” IEEE J. Sel. Areas Commun. , vol. 35, no. 12, pp. 2696–2707, Dec. 2017.
  10. [10] X. Jing, M. Li, H. Liu, S. Li, and G. Pan, “Superimposed pilot optimization design and channel estimation for multiuser massive MIMO systems,” IEEE Trans. Veh. Technol. , vol. 67, no. 12, pp. 11 818–11 832, Dec. 2018.
  11. [11] C. Qian, R. Gu, W. Xu, J. Xu, and X. You, “Enhancing wideband multiuser MIMO uplink using superimposed pilots: Joint receiver design,” IEEE Wireless Commun. Lett. , vol. 13, no. 4, pp. 1138–1142, Apr. 2024.
  12. [12] X. Li et al. , “Learning-aided iterative receiver for superimposed pilots: Design and experimental evaluation,” IEEE Trans. Wireless Commun. , vol. 25, pp. 13 864–13 880, 2026.
  13. [13] X. Li, X. Zhou, J. Zhang, C.-K. Wen, and S. Jin, “AI-driven iterative receiver for superimposed pilot schemes in MIMO-OFDM systems,” in Proc. IEEE Wireless Commun. Netw. Conf. (WCNC) , Milan, Italy, Mar. 2025, pp. 1–6.
  14. [14] R. Zhang et al. , “Score-based conditional flow models for MIMO receiver design with superimposed pilots,” IEEE Open J. Commun. Soc. , vol. 7, pp. 3331–3345, 2026.
  15. [15] M. Ghogho, D. McLernon, E. Alameda-Hernandez, and A. Swami, “Channel estimation and symbol detection for block transmission using data-dependent superimposed training,” IEEE Signal Process. Lett. , vol. 12, no. 3, pp. 226–229, Mar. 2005.
  16. [16] Y. Wu and S. Sugiura, “Reduced-overhead channel estimation and iterative detection of FTN signaling based on pilot superimposition and spectral interference alignment,” in Proc. IEEE Global Commun. Conf. (GLOBECOM) , Taipei, Taiwan, Dec. 2025, pp. 5820–5825.
  17. [17] M. Ghogho and A. Swami, “Estimation of doubly-selective channels in block transmissions using data-dependent superimposed training,” in Proc. 14th Eur. Signal Process. Conf. (EUSIPCO) , Florence, Italy, Sept. 2006, pp. 1–5.
  18. [18] S. He and J. K. Tugnait, “On doubly selective channel estimation using sperimposed training and discrete prolate spheroidal sequences,” IEEE Trans. Signal Process. , vol. 56, no. 7, pp. 3214–3228, Jul. 2008.
  19. [19] R. Carrasco-Alvarez, R. Parra-Michel, and A. G. Orozco-Lugo, “Enhanced time-varying channel estimation based on two dimensional basis projection and self-interference suppression,” in Proc. IEEE 11th Int. Workshop Signal Process. Adv. Wireless Commun. (SPAWC) , Marrakech, Morocco, Jun. 2010, pp. 1–5.
  20. [20] K.-C. Chan, W.-C. Huang, C.-P. Li, and H.-J. Li, “Investigation on data identification problem for data-dependent superimposed training,” in Proc. IEEE 75th Veh. Technol. Conf. (VTC Spring) , Yokohama, Japan, May 2012, pp. 1–5.