{"ID":2870194,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.12694","arxiv_id":"2509.12694","title":"Soft Graph Transformer for MIMO Detection","abstract":"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.","short_abstract":"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 assump...","url_abs":"https://arxiv.org/abs/2509.12694","url_pdf":"https://arxiv.org/pdf/2509.12694v5","authors":"[\"Jiadong Hong\",\"Lei Liu\",\"Xinyu Bian\",\"Wenjie Wang\",\"Zhaoyang Zhang\"]","published":"2025-09-16T05:42:45Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.IT\",\"eess.SP\"]","methods":"[\"Transformer\"]","has_code":false}