A Model-Driven Deep Learning Algorithm for Joint Activity Detection and Channel Estimation

This letter provides a deep learning framework for massive grant-free random access in 6G cellular internet of things (IoT) networks. A model-driven deep learning algorithm for joint activity detection and channel estimation is proposed based on the principle of approximate massage passing (AMP). This algorithm only needs to learn four key parameters, but not the whole algorithm architecture. More importantly, it does not require the prior information about active probabilities and channel variance, and can significantly improve the performance with a finite number of training data. Simulation results validate the effectiveness of the proposed deep learning algorithm.