用稀疏注意力建模无线信道时空演化，提升预测精度与泛化能力
LWM-Temporal: Sparse Spatio-Temporal Attention for Wireless Channel Representation Learning
- 在角度-时延-时间域使用稀疏时空注意力，只关注物理上合理的邻域
- 自监督预训练下信道预测性能优于基线，长时程和小样本场景更显著
- 适合需要高效通用信道表示的无线系统设计与智能通信研究者
LWM-Temporal 是大型无线模型（LWM）家族的新成员，旨在捕捉无线信道的时空特性。作为任务无关的基础模型，它学习可复用于多种下游任务的通用信道嵌入，以表征移动引起的演化过程。该模型在角度-时延-时间域运行，引入稀疏时空注意力（SSTA），一种与传播对齐的注意力机制，将交互限制在物理上合理的邻域，使注意力复杂度降低一个数量级，同时保持几何一致的依赖关系。模型通过融合物理信息的掩码课程进行自监督预训练，模拟真实遮挡、导频稀疏性和测量失真。在多个运动场景下的信道预测实验中，其性能持续优于强基线，尤其在长时程预测和有限微调数据条件下表现突出，凸显了几何感知架构与几何一致预训练对于学习可迁移时空无线表示的重要性。
原文摘要 · Abstract (English)
LWM-Temporal is a new member of the Large Wireless Models (LWM) family that targets the spatiotemporal nature of wireless channels. Designed as a task-agnostic foundation model, LWM-Temporal learns universal channel embeddings that capture mobility-induced evolution and are reusable across various downstream tasks. To achieve this objective, LWM-Temporal operates in the angle-delay-time domain and introduces Sparse Spatio-Temporal Attention (SSTA), a propagation-aligned attention mechanism that restricts interactions to physically plausible neighborhoods, reducing attention complexity by an order of magnitude while preserving geometry-consistent dependencies. LWM-Temporal is pretrained in a self-supervised manner using a physics-informed masking curriculum that emulates realistic occlusions, pilot sparsity, and measurement impairments. Experimental results on channel prediction across multiple mobility regimes show consistent improvements over strong baselines, particularly under long horizons and limited fine-tuning data, highlighting the importance of geometry-aware architectures and geometry-consistent pretraining for learning transferable spatiotemporal wireless representations.
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。