Soft Graph Diffusion Transformer for MIMO Detection

TL;DR

The paper introduces SGDiT, a novel flow-based neural network for MIMO detection that models the process as a progressive denoising task, achieving competitive BER performance and good generalization.

Contribution

It proposes a flow matching perspective and a soft graph diffusion transformer with stage-aware information integration for improved neural MIMO detection.

Findings

SGDiT achieves competitive BER performance across various MIMO configurations.

The model generalizes well across different channel conditions.

Using a cross-entropy loss aligns better with the discrete nature of symbol detection.

Abstract

Learning-based MIMO detection has shown strong empirical performance, yet existing methods typically rely on fixed-depth architectures without explicitly modeling the progressive refinement of symbol estimates. In this paper, we revisit MIMO detection from a flow matching perspective and propose the Soft Graph Diffusion Transformer (SGDiT), which reformulates detection as a noise-level-conditioned denoising process that progressively transforms a Gaussian initialization toward the posterior conditioned on channel observations. An adaptive layer normalization (AdaLN)-conditioned soft graph transformer is employed to parameterize the denoising dynamics, enabling stage-aware information integration between observation and symbol domains. To better align with the discrete nature of symbol detection, we further adopt a cross-entropy-based training objective that directly models bit-wise posterior probabilities, providing a more suitable inductive bias than conventional regression-based formulations. Experimental results across various MIMO system configurations demonstrate that SGDiT achieves competitive bit error rate (BER) performance compared with representative baselines. Furthermore, the proposed model exhibits good generalization capability across different channel conditions. Overall, the SGDiT framework provides an effective and practical approach for neural MIMO detection.