Soft Graph Transformer for MIMO Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hong, Jiadong, Liu, Lei, Bian, Xinyu, Wang, Wenjie, Zhang, Zhaoyang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915934211407872
author Hong, Jiadong
Liu, Lei
Bian, Xinyu
Wang, Wenjie
Zhang, Zhaoyang
author_facet Hong, Jiadong
Liu, Lei
Bian, Xinyu
Wang, Wenjie
Zhang, Zhaoyang
contents We propose the Soft Graph Transformer (SGT), a soft-input-soft-output neural architecture designed for MIMO detection. While Maximum Likelihood (ML) detection achieves optimal accuracy, its exponential complexity makes it infeasible in large systems, and conventional message-passing algorithms rely on asymptotic assumptions that often fail in finite dimensions. Recent Transformer-based detectors show strong performance but typically overlook the MIMO factor graph structure and cannot exploit prior soft information. SGT addresses these limitations by combining self-attention, which encodes contextual dependencies within symbol and constraint subgraphs, with graph-aware cross-attention, which performs structured message passing across subgraphs. Its soft-input interface allows the integration of auxiliary priors, producing effective soft outputs while maintaining computational efficiency. Experiments demonstrate that SGT achieves near-ML performance and offers a flexible and interpretable framework for receiver systems that leverage soft priors.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12694
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Soft Graph Transformer for MIMO Detection
Hong, Jiadong
Liu, Lei
Bian, Xinyu
Wang, Wenjie
Zhang, Zhaoyang
Machine Learning
Information Theory
Signal Processing
We propose the Soft Graph Transformer (SGT), a soft-input-soft-output neural architecture designed for MIMO detection. While Maximum Likelihood (ML) detection achieves optimal accuracy, its exponential complexity makes it infeasible in large systems, and conventional message-passing algorithms rely on asymptotic assumptions that often fail in finite dimensions. Recent Transformer-based detectors show strong performance but typically overlook the MIMO factor graph structure and cannot exploit prior soft information. SGT addresses these limitations by combining self-attention, which encodes contextual dependencies within symbol and constraint subgraphs, with graph-aware cross-attention, which performs structured message passing across subgraphs. Its soft-input interface allows the integration of auxiliary priors, producing effective soft outputs while maintaining computational efficiency. Experiments demonstrate that SGT achieves near-ML performance and offers a flexible and interpretable framework for receiver systems that leverage soft priors.
title Soft Graph Transformer for MIMO Detection
topic Machine Learning
Information Theory
Signal Processing
url https://arxiv.org/abs/2509.12694