# Auto-CsiNet: Scenario-customized Automatic Neural Network Architecture Generation for Massive MIMO CSI Feedback

arXiv: https://arxiv.org/abs/2311.15950 · HTML: https://mlsanity.com/paper/2311.15950/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 51 references that are in the map.
- First posted on arXiv 27 Nov 2023.

## Builds on (most cited first, 23 of 23)

- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [AutoML: A Survey of the State-of-the-Art](https://mlsanity.com/paper/1908.00709/) (2019)
- [Large-Scale Evolution of Image Classifiers](https://mlsanity.com/paper/1703.01041/) (2017)
- [PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search](https://mlsanity.com/paper/1907.05737/) (2019)
- [A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions](https://mlsanity.com/paper/2006.02903/) (2020)
- [Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets](https://mlsanity.com/paper/1605.07079/) (2016)
- [Deep Learning-Based Communication Over the Air](https://mlsanity.com/paper/1707.03384/) (2017)
- [AutoML to Date and Beyond: Challenges and Opportunities](https://mlsanity.com/paper/2010.10777/) (2020)
- [Toward a 6G AI-Native Air Interface](https://mlsanity.com/paper/2012.08285/) (2020)
- [Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems](https://mlsanity.com/paper/2206.14383/) (2022)
- [Convolutional Neural Network based Multiple-Rate Compressive Sensing for Massive MIMO CSI Feedback: Design, Simulation, and Analysis](https://mlsanity.com/paper/1906.06007/) (2019)
- [Multi-resolution CSI Feedback with deep learning in Massive MIMO System](https://mlsanity.com/paper/1910.14322/) (2019)
- [Deep Learning for Physical-Layer 5G Wireless Techniques: Opportunities, Challenges and Solutions](https://mlsanity.com/paper/1904.09673/) (2019)
- [CLNet: Complex Input Lightweight Neural Network designed for Massive MIMO CSI Feedback](https://mlsanity.com/paper/2102.07507/) (2021)
- [A Speculative Study on 6G](https://mlsanity.com/paper/1902.06700/) (2019)
- [Lightweight Convolutional Neural Networks for CSI Feedback in Massive MIMO](https://mlsanity.com/paper/2005.00438/) (2020)
- [Model-Driven Deep Learning Based Channel Estimation and Feedback for Millimeter-Wave Massive Hybrid MIMO Systems](https://mlsanity.com/paper/2104.11052/) (2021)
- [Dilated Convolution based CSI Feedback Compression for Massive MIMO Systems](https://mlsanity.com/paper/2106.04043/) (2021)
- [PRVNet: A Novel Partially-Regularized Variational Autoencoders for Massive MIMO CSI Feedback](https://mlsanity.com/paper/2011.04178/) (2020)
- [A Spatially Separable Attention Mechanism for massive MIMO CSI Feedback](https://mlsanity.com/paper/2208.03369/) (2022)
- [A Lightweight Deep Network for Efficient CSI Feedback in Massive MIMO Systems](https://mlsanity.com/paper/2105.10283/) (2021)
- [Attention Mechanism Based Intelligent Channel Feedback for mmWave Massive MIMO Systems](https://mlsanity.com/paper/2208.06570/) (2022)

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

- [MultiPathFormer: Towards a Foundation Model for Multipath Wireless Propagation](https://mlsanity.com/paper/2608.05076/) (2026)

## Abstract (arXiv)

Deep learning has revolutionized the design of the channel state information (CSI) feedback module in wireless communications. However, designing the optimal neural network (NN) architecture for CSI feedback can be a laborious and time-consuming process. Manual design can be prohibitively expensive for customizing NNs to different scenarios. This paper proposes using neural architecture search (NAS) to automate the generation of scenario-customized CSI feedback NN architectures, thereby maximizing the potential of deep learning in exclusive environments. By employing automated machine learning and gradient-descent-based NAS, an efficient and cost-effective architecture design process is achieved. The proposed approach leverages implicit scene knowledge, integrating it into the scenario customization process in a data-driven manner, and fully exploits the potential of deep learning for each specific scenario. To address the issue of excessive search, early stopping and elastic selection mechanisms are employed, enhancing the efficiency of the proposed scheme. The experimental results demonstrate that the automatically generated architecture, known as Auto-CsiNet, outperforms manually-designed models in both reconstruction performance (achieving approximately a 14% improvement) and complexity (reducing it by approximately 50%). Furthermore, the paper analyzes the impact of the scenario on the NN architecture and its capacity.