Detect to Learn: Structure Learning with Attention and Decision Feedback for MIMO-OFDM Receive Processing

TL;DR

This paper presents RC-AttStructNet-DF, an online attention-based method that improves MIMO-OFDM data detection by effectively utilizing pilot and data symbols through decision feedback and advanced neural network modules.

Contribution

It introduces a novel online attention-based framework combining reservoir computing and multi-head attention for improved MIMO-OFDM detection with dynamic updates.

Findings

Enhanced detection accuracy in MIMO-OFDM systems

Effective exploitation of pilot and data symbols

Robust performance across various scenarios

Abstract

The limited over-the-air (OTA) pilot symbols in multiple-input-multiple-output orthogonal-frequency-division-multiplexing (MIMO-OFDM) systems presents a major challenge for detecting transmitted data symbols at the receiver, especially for machine learning-based approaches. While it is crucial to explore effective ways to exploit pilots, one can also take advantage of the data symbols to improve detection performance. Thus, this paper introduces an online attention-based approach, namely RC-AttStructNet-DF, that can efficiently utilize pilot symbols and be dynamically updated with the detected payload data using the decision feedback (DF) mechanism. Reservoir computing (RC) is employed in the time domain network to facilitate efficient online training. The frequency domain network adopts the novel 2D multi-head attention (MHA) module to capture the time and frequency correlations, and the structural-based StructNet to facilitate the DF mechanism. The attention loss is designed to learn the frequency domain network. The DF mechanism further enhances detection performance by dynamically tracking the channel changes through detected data symbols. The effectiveness of the RC-AttStructNet-DF approach is demonstrated through extensive experiments in MIMO-OFDM and massive MIMO-OFDM systems with different modulation orders and under various scenarios.