用Transformer思想设计的MIMO接收机，性能逼近最优且复杂度可控。
A Transformer Inspired AI-based MIMO receiver
- 将发射层视为令牌，用轻量自注意力建模流间干扰
- 在5G真实信道下接近最优误码率，多项式复杂度可预测
- 结合物理模型可解释性与数据驱动灵活性，适合通信系统优化
我们提出AttDet，一种受Transformer启发的MIMO检测方法，将每个发射层视为一个令牌，通过轻量自注意力机制学习流间干扰。查询和键直接从估计的信道矩阵中获取，注意力分数反映信道相关性；值初始化为匹配滤波输出并迭代优化。该设计融合了基于模型的可解释性与数据驱动的灵活性。在真实5G信道模型及高阶混合QAM调制编码方案下的链路级仿真表明，AttDet可逼近近似最优的比特误码率/块误码率性能，同时保持可预测的多项式复杂度。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。