A Transformer Inspired AI-based MIMO receiver

TL;DR

AttDet is a novel Transformer-inspired MIMO detection method that leverages self-attention to model inter-stream interference, combining interpretability with high-performance detection in realistic 5G scenarios.

Contribution

Introduces AttDet, a Transformer-based MIMO detector that uses channel-aware attention mechanisms for improved interference modeling and near-optimal performance.

Findings

Achieves near-optimal BER/BLER performance in simulations.

Maintains polynomial complexity suitable for practical deployment.

Demonstrates robustness under realistic 5G channel conditions.

Abstract

We present AttDet, a Transformer-inspired MIMO (Multiple Input Multiple Output) detection method that treats each transmit layer as a token and learns inter-stream interference via a lightweight self-attention mechanism. Queries and keys are derived directly from the estimated channel matrix, so attention scores quantify channel correlation. Values are initialized by matched-filter outputs and iteratively refined. The AttDet design combines model-based interpretability with data-driven flexibility. We demonstrate through link-level simulations under realistic 5G channel models and high-order, mixed QAM modulation and coding schemes, that AttDet can approach near-optimal BER/BLER (Bit Error Rate/Block Error Rate) performance while maintaining predictable, polynomial complexity.