# Deep Generative Models for Downlink Channel Estimation in FDD Massive MIMO Systems

arXiv: https://arxiv.org/abs/2203.04935 · HTML: https://mlsanity.com/paper/2203.04935/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 60 references that are in the map.
- First posted on arXiv 9 Mar 2022.

## Builds on (most cited first, 17 of 17)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Lipschitz regularity of deep neural networks: analysis and efficient estimation](https://mlsanity.com/paper/1805.10965/) (2018)
- [Regularisation of Neural Networks by Enforcing Lipschitz Continuity](https://mlsanity.com/paper/1804.04368/) (2018)
- [Mode Regularized Generative Adversarial Networks](https://mlsanity.com/paper/1612.02136/) (2016)
- [DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications](https://mlsanity.com/paper/1902.06435/) (2019)
- [Deep Learning for mmWave Beam and Blockage Prediction Using Sub-6GHz Channels](https://mlsanity.com/paper/1910.02900/) (2019)
- [Millimeter Wave Channel Modeling and Cellular Capacity Evaluation](https://mlsanity.com/paper/1312.4921/) (2013)
- [Deep Learning for TDD and FDD Massive MIMO: Mapping Channels in Space and Frequency](https://mlsanity.com/paper/1905.03761/) (2019)
- [Deep Learning based Downlink Channel Prediction for FDD Massive MIMO System](https://mlsanity.com/paper/1908.03360/) (2019)
- [Deep Learning for Direct Hybrid Precoding in Millimeter Wave Massive MIMO Systems](https://mlsanity.com/paper/1905.13212/) (2019)
- [3D Scene Based Beam Selection for mmWave Communications](https://mlsanity.com/paper/1911.08409/) (2019)
- [FDD Massive MIMO Uplink and Downlink Channel Reciprocity Properties: Full or Partial Reciprocity?](https://mlsanity.com/paper/1912.11221/) (2019)
- [FDD Massive MIMO Channel Estimation with Arbitrary 2D-Array Geometry](https://mlsanity.com/paper/1711.06548/) (2017)
- [Enabling FDD Massive MIMO through Deep Learning-based Channel Prediction](https://mlsanity.com/paper/1901.03664/) (2019)
- [Tensor-Based Channel Estimation for Dual-Polarized Massive MIMO Systems](https://mlsanity.com/paper/1805.02223/) (2018)
- [Downlink Extrapolation for FDD Multiple Antenna Systems Through Neural Network Using Extracted Uplink Path Gains](https://mlsanity.com/paper/2004.01361/) (2020)

## Built on by (most cited first, 1 of 1)

- [Mixture-of-Experts Diffusion Models for Adaptive Massive MIMO Channel Estimation via Variational Bayesian Inference](https://mlsanity.com/paper/2605.18325/) (2026)

## Abstract (arXiv)

It is well accepted that acquiring downlink channel state information in frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems is challenging because of the large overhead in training and feedback. In this paper, we propose a deep generative model (DGM)-based technique to address this challenge. Exploiting the partial reciprocity of uplink and downlink channels, we first estimate the frequency-independent underlying channel parameters, i.e., the magnitudes of path gains, delays, angles-of-arrivals (AoAs) and angles-of-departures (AoDs), via uplink training, since these parameters are common in both uplink and downlink. Then, the frequency-specific underlying channel parameters, namely, the phase of each propagation path, are estimated via downlink training using a very short training signal. In the first step, we incorporate the underlying distribution of the channel parameters as a prior into our channel estimation algorithm. We use DGMs to learn this distribution. Simulation results indicate that our proposed DGM-based channel estimation technique outperforms, by a large gap, the conventional channel estimation techniques in practical ranges of signal-to-noise ratio (SNR). In addition, a near-optimal performance is achieved using only few downlink pilot measurements.