EqDeepRx: Learning a Scalable MIMO Receiver

TL;DR

EqDeepRx introduces a scalable, explainable deep learning-based MIMO receiver that combines traditional channel estimation with neural network modules, achieving improved error rates and spectral efficiency across various scenarios.

Contribution

The paper presents EqDeepRx, a novel MIMO receiver architecture that scales linearly with multiplexing order and enhances explainability by integrating conventional processing with neural networks.

Findings

Improved error rate performance in simulations.

Enhanced spectral efficiency over baseline methods.

Supports multiple MIMO configurations without retraining.

Abstract

While machine learning (ML)-based receiver algorithms have received a great deal of attention in the recent literature, they often suffer from poor scaling with increasing spatial multiplexing order and lack of explainability and generalization. This paper presents EqDeepRx, a practical deep-learning-aided multiple-input multiple-output (MIMO) receiver, which is built by augmenting linear receiver processing with carefully engineered ML blocks. At the core of the receiver model is a shared-weight DetectorNN that operates independently on each spatial stream or layer, enabling near-linear complexity scaling with respect to multiplexing order. To ensure better explainability and generalization, EqDeepRx retains conventional channel estimation and augments it with a lightweight DenoiseNN that learns frequency-domain smoothing. To reduce the dimensionality of the DetectorNN inputs, the receiver utilizes two linear equalizers in parallel: a linear minimum mean-square error (LMMSE) equalizer with interference-plus-noise covariance estimation and a regularized zero-forcing (RZF) equalizer. The parallel equalized streams are jointly consumed by the DetectorNN, after which a compact DemapperNN produces bit log-likelihood ratios for channel decoding. 5G/6G-compliant end-to-end simulations across multiple channel scenarios, pilot patterns, and inter-cell interference conditions show improved error rate and spectral efficiency over a conventional baseline, while maintaining low-complexity inference and support for different MIMO configurations without retraining.