# Learning Representations for CSI Adaptive Quantization and Feedback

arXiv: https://arxiv.org/abs/2207.06924 · HTML: https://mlsanity.com/paper/2207.06924/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 13 Jul 2022.

## Builds on (most cited first, 9 of 9)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Tune: A Research Platform for Distributed Model Selection and Training](https://mlsanity.com/paper/1807.05118/) (2018)
- [Learning Ordered Representations with Nested Dropout](https://mlsanity.com/paper/1402.0915/) (2014)
- [Changeable Rate and Novel Quantization for CSI Feedback Based on Deep Learning](https://mlsanity.com/paper/2202.13627/) (2022)
- [Machine Learning-Based CSI Feedback With Variable Length in FDD Massive MIMO](https://mlsanity.com/paper/2204.04723/) (2022)
- [Binarized Aggregated Network with Quantization: Flexible Deep Learning Deployment for CSI Feedback in Massive MIMO System](https://mlsanity.com/paper/2105.00354/) (2021)
- [Learning the CSI Denoising and Feedback Without Supervision](https://mlsanity.com/paper/2104.05002/) (2021)

## Built on by (most cited first, 3 of 3)

- [Quantization Adaptor for Bit-Level Deep Learning-Based Massive MIMO CSI Feedback](https://mlsanity.com/paper/2211.02937/) (2022)
- [Streamlining Multimodal Data Fusion in Wireless Communication and Sensor Networks](https://mlsanity.com/paper/2302.12636/) (2023)
- [An Efficient Network with Novel Quantization Designed for Massive MIMO CSI Feedback](https://mlsanity.com/paper/2405.20068/) (2024)

## Abstract (arXiv)

In this work, we propose an efficient method for channel state information (CSI) adaptive quantization and feedback in frequency division duplexing (FDD) systems. Existing works mainly focus on the implementation of autoencoder (AE) neural networks (NNs) for CSI compression, and consider straightforward quantization methods, e.g., uniform quantization, which are generally not optimal. With this strategy, it is hard to achieve a low reconstruction error, especially, when the available number of bits reserved for the latent space quantization is small. To address this issue, we recommend two different methods: one based on a post training quantization and the second one in which the codebook is found during the training of the AE. Both strategies achieve better reconstruction accuracy compared to standard quantization techniques.