EqDeepRx: Learning a Scalable MIMO Receiver

2026-02-12

AI Summary

This work proposes a scalable MIMO receiver architecture that integrates classical signal processing with lightweight neural networks to overcome the poor scalability, lack of interpretability, and limited generalization of conventional receivers under high-order spatial multiplexing. The design employs a shared-weight DetectorNN to achieve near-linear complexity scaling, combined with LMMSE/RZF equalizers, a frequency-domain DenoiseNN, and a compact DemapperNN. By preserving traditional modules such as channel estimation while enhancing performance through neural augmentation, the proposed receiver adapts seamlessly to diverse MIMO configurations without retraining. End-to-end simulations in 5G/6G scenarios demonstrate significant improvements over conventional baselines, achieving substantially lower bit error rates, higher spectral efficiency, and low inference complexity.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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.

Problem

• MIMO receiver
• scalability
• explainability
• generalization
• spatial multiplexing

Innovation

• MIMO receiver
• deep learning
• scalable architecture
• explainable AI
• linear equalization