mlsanityData to 14 Oct 2026

Precoder Design in Multi-User FDD Systems with VQ-VAE and GNN

arXiv 2510.09495 ↗First posted 10 Oct 2025cs.IT cs.AI eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

Robust precoding is efficiently feasible in frequency division duplex (FDD) systems by incorporating the learnt statistics of the propagation environment through a generative model. We build on previous work that successfully designed site-specific precoders based on a combination of Gaussian mixture models (GMMs) and graph neural networks (GNNs). In this paper, by utilizing a vector quantized-variational autoencoder (VQ-VAE), we circumvent one of the key drawbacks of GMMs, i.e., the number of GMM components scales exponentially to the feedback bits. In addition, the deep learning architecture of the VQ-VAE allows us to jointly train the GNN together with VQ-VAE along with pilot optimization forming an end-to-end (E2E) model, resulting in considerable performance gains in sum rate for multi-user wireless systems. Simulations demonstrate the superiority of the proposed frameworks over the conventional methods involving the sub-discrete Fourier transform (DFT) pilot matrix and iterative precoder algorithms enabling the deployment of systems characterized by fewer pilots or feedback bits.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 22 references that are in the map. First posted on arXiv 10 Oct 2025.

Builds on

12 of 22 references.

References · 12

  1. 2017Neural Discrete Representation Learningcited by 4,712
  2. 2019A Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research Problemscited by 160
  3. 2023Blockwise Self-Supervised Learning at Scalecited by 22
  4. 2022Variational Autoencoder Leveraged MMSE Channel Estimationcited by 9
  5. 2022Multidimensional Graph Neural Networks for Wireless Communicationscited by 7
  6. 2022Role of Deep Learning in Wireless Communicationscited by 6
  7. 2021Learning the CSI Denoising and Feedback Without Supervisioncited by 3
  8. 2022Evaluation of a Gaussian Mixture Model-based Channel Estimator using Measurement Datacited by 2
  9. 2024A Statistical Characterization of Wireless Channels Conditioned on Side Informationcited by 2
  10. 2017Millimeter-Wave Beamformed Full-dimensional MIMO Channel Estimation Based on Atomic Norm Minimizationcited by 1
  11. 2024Feedback Design with VQ-VAE for Robust Precoding in Multi-User FDD Systemscited by 1
  12. 2024Statistical Precoder Design in Multi-User Systems via Graph Neural Networks and Generative Modelingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Scalable Transceiver Design for Multi-User Communication in FDD Massive MIMO Systems via Deep Learning
  2. 2025A Low-Complexity Plug-and-Play Deep Learning Model for Massive MIMO Precoding Across Sites
  3. 2025Learning to Quantize and Precode in Massive MIMO Systems for Energy Reduction: a Graph Neural Network Approach
  4. 2024Augmenting Training Data with Vector-Quantized Variational Autoencoder for Classifying RF Signals
  5. 2021Learning-Based Symbol Level Precoding: A Memory-Efficient Unsupervised Learning Approach
  6. 2025Asymptotic Analysis of One-bit Quantized Box-Constrained Precoding in Large-Scale Multi-User Systems
  7. 2024Integrating Pre-Trained Language Model with Physical Layer Communications
  8. 2022Learning Representations for CSI Adaptive Quantization and Feedback