Deep Learning for Large Intelligent Surfaces with Sparse Sensors


A deep learning based large intelligent surface (LIS) interaction design using a novel LIS architecture

Key ideas

  • Enabling LISs for mmWave and massive MIMO systems
  • Novel LIS architecture enabling energy- and training-efficient interaction designs
  • Two interaction design solutions: compressive sensing and deep learning solutions
  • Recovering full channels from a few channel estimates using compressive sensing
  • Leveraging deep learning to predict interaction beams from a few channel estimates
  • Approaching optimal rates with a few active sensors and almost no training overhead


  • Reduce beam training and precoding design overhead in LIS aided mmWave and massive MIMO systems while still enabling energy-efficient LIS surfaces

More information about this research direction

Paper: A. Taha, M. Alrabeiah and A. Alkhateeb, “Enabling Large Intelligent Surfaces With Compressive Sensing and Deep Learning,” in IEEE Access, vol. 9, pp. 44304-44321, 2021.

Abstract: Employing large intelligent surfaces (LISs) is a promising solution for improving the coverage and rate of future wireless systems. These surfaces comprise massive numbers of nearly-passive elements that interact with the incident signals, for example by reflecting them, in a smart way that improves the wireless system performance. Prior work focused on the design of the LIS reflection matrices assuming full channel knowledge. Estimating these channels at the LIS, however, is a key challenging problem. With the massive number of LIS elements, channel estimation or reflection beam training will be associated with (i) huge training overhead if all the LIS elements are passive (not connected to a baseband) or with (ii) prohibitive hardware complexity and power consumption if all the elements are connected to the baseband through a fully-digital or hybrid analog/digital architecture. This paper proposes efficient solutions for these problems by leveraging tools from compressive sensing and deep learning. First, a novel LIS architecture based on sparse channel sensors is proposed. In this architecture, all the LIS elements are passive except for a few elements that are active (connected to the baseband). We then develop two solutions that design the LIS reflection matrices with negligible training overhead. In the first approach, we leverage compressive sensing tools to construct the channels at all the LIS elements from the channels seen only at the active elements. In the second approach, we develop a deep-learning based solution where the LIS learns how to interact with the incident signal given the channels at the active elements, which represent the state of the environment and transmitter/receiver locations. We show that the achievable rates of the proposed solutions approach the upper bound, which assumes perfect channel knowledge, with negligible training overhead and with only a few active elements, making them promising for future LIS systems.


  author={Taha, Abdelrahman and Alrabeiah, Muhammad and Alkhateeb, Ahmed},

  journal={IEEE Access}, 

  title={Enabling Large Intelligent Surfaces With Compressive Sensing and Deep Learning}, 






To reproduce the results in this paper:

Simulation codes (based on DeepMIMO v1):
These simulations use the DeepMIMO scenarios:
Example: Steps to generate the results in this figure
  1. Download all the files of this GitHub project and add them to the “DeepMIMO_Dataset_Generation” folder. (Note that the DeepMIMO source data are available on this link).
  2. Run the file named “Fig12_generator.m” in MATLAB and the script will sequentially execute the following tasks:
    • Generate the inputs and outputs of the deep learning model
    • Build, train, and test the deep learning model
    • Process the deep learning outputs and generate the performance results.

Having questions or feedback?

Send an email to 


Or post your question in the DeepMIMO forum