Model-Driven Deep Learning for MIMO Detection
This work addresses MIMO detection for wireless communication systems, offering an incremental improvement by combining model-driven design with deep learning for enhanced efficiency and robustness.
The paper tackles MIMO detection by proposing a model-driven deep learning approach that unfolds an iterative algorithm with few trainable parameters, enabling rapid training with small datasets and extending to soft-input soft-output detection; numerical results show it significantly improves performance over traditional iterative detectors, outperforms other DL-based detectors, and exhibits superior robustness to mismatches.
In this paper, we investigate the model-driven deep learning (DL) for MIMO detection. In particular, the MIMO detector is specially designed by unfolding an iterative algorithm and adding some trainable parameters. Since the number of trainable parameters is much fewer than the data-driven DL based signal detector, the model-driven DL based MIMO detector can be rapidly trained with a much smaller data set. The proposed MIMO detector can be extended to soft-input soft-output detection easily. Furthermore, we investigate joint MIMO channel estimation and signal detection (JCESD), where the detector takes channel estimation error and channel statistics into consideration while channel estimation is refined by detected data and considers the detection error. Based on numerical results, the model-driven DL based MIMO detector significantly improves the performance of corresponding traditional iterative detector, outperforms other DL-based MIMO detectors and exhibits superior robustness to various mismatches.