# Deep Learning Based RIS Channel Extrapolation with Element-grouping

arXiv: https://arxiv.org/abs/2105.06850 · HTML: https://mlsanity.com/paper/2105.06850/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 14 May 2021.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications](https://mlsanity.com/paper/1902.06435/) (2019)
- [Towards Smart and Reconfigurable Environment: Intelligent Reflecting Surface Aided Wireless Network](https://mlsanity.com/paper/1905.00152/) (2019)
- [Federated Learning for Channel Estimation in Conventional and RIS-Assisted Massive MIMO](https://mlsanity.com/paper/2008.10846/) (2020)
- [Holographic MIMO Surfaces for 6G Wireless Networks: Opportunities, Challenges, and Trends](https://mlsanity.com/paper/1911.12296/) (2019)
- [Intelligent Reflecting Surface-Enhanced OFDM: Channel Estimation and Reflection Optimization](https://mlsanity.com/paper/1909.03272/) (2019)
- [Deep Learning based Channel Extrapolation for Large-Scale Antenna Systems: Opportunities, Challenges and Solutions](https://mlsanity.com/paper/2102.12859/) (2021)
- [Wireless Communications with Programmable Metasurface: New Paradigms, Opportunities, and Challenges on Transceiver Design](https://mlsanity.com/paper/1907.01956/) (2019)
- [Deep-Learning-Aided Detection for Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/1910.09136/) (2019)

## Built on by (most cited first, 2 of 2)

- [Deep-Learning Channel Estimation for IRS-Assisted Integrated Sensing and Communication System](https://mlsanity.com/paper/2402.09441/) (2024)
- [Extreme Learning Machine-based Channel Estimation in IRS-Assisted Multi-User ISAC System](https://mlsanity.com/paper/2402.09440/) (2024)

## Abstract (arXiv)

Reconfigurable intelligent surface (RIS) is considered as a revolutionary technology for future wireless communication networks. In this letter, we consider the acquisition of the cascaded channels, which is a challenging task due to the massive number of passive RIS elements. To reduce the pilot overhead, we adopt the element-grouping strategy, where each element in one group shares the same reflection coefficient and is assumed to have the same channel condition. We analyze the channel interference caused by the element-grouping strategy and further design two deep learning based networks. The first one aims to refine the partial channels by eliminating the interference, while the second one tries to extrapolate the full channels from the refined partial channels. We cascade the two networks and jointly train them. Simulation results show that the proposed scheme provides significant gain compared to the conventional element-grouping method without interference elimination.