{"ID":2857643,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.09495","arxiv_id":"2510.09495","title":"Precoder Design in Multi-User FDD Systems with VQ-VAE and GNN","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2510.09495","url_pdf":"https://arxiv.org/pdf/2510.09495v1","authors":"[\"Srikar Allaparapu\",\"Michael Baur\",\"Benedikt Böck\",\"Michael Joham\",\"Wolfgang Utschick\"]","published":"2025-10-10T15:55:18Z","proceeding":"cs.IT","tasks":"[\"cs.IT\",\"cs.AI\",\"eess.SP\"]","methods":"[\"Graph Neural Network\",\"Variational Autoencoder\"]","has_code":false}