DeMa：双路径延迟感知Mamba用于高效多变量时间序列分析
DeMa: Dual-Path Delay-Aware Mamba for Efficient Multivariate Time Series Analysis
AI总结：
DeMa通过双路径架构改进Mamba，解决多变量时间序列分析中的延迟建模、跨变量依赖和时间动态分离问题，实现高效且准确的分析。
摘要：
准确且高效的多变量时间序列（MTS）分析对广泛智能应用越来越关键。在这一领域，Transformer因其强大的捕捉成对依赖能力而成为主导架构。然而，基于Transformer的模型存在二次计算复杂度和高内存开销，限制了其在长期和大规模MTS建模中的可扩展性和实用性。最近，Mamba作为一种线性时间替代方案出现，具有高表达能力。然而，直接应用原始Mamba到MTS仍不理想，因为存在三个关键限制：（i）缺乏显式的跨变量建模，（ii）难以分离纠缠的系列内时间动态和系列间交互，（iii）对潜在时间滞后交互效应的建模不足。这些问题限制了其在多样MTS任务中的有效性。为了解决这些挑战，我们提出了DeMa，一种双路径延迟感知Mamba骨干网络。DeMa保留了Mamba的线性复杂度优势，同时显著提高了其在MTS设置中的适用性。具体而言，DeMa引入了三个关键创新：（i）它将MTS分解为系列内时间动态和系列间交互；（ii）它开发了一个时间路径，包含Mamba-SSD模块，以捕捉每个单独系列内的长程动态，实现系列无关的并行计算；（iii）它设计了一个变量路径，包含Mamba-DALA模块，通过延迟感知线性注意力模块来建模跨变量依赖。在五个代表性任务（长期和短期预测、数据插补、异常检测和系列分类）上的广泛实验表明，DeMa在达到最先进性能的同时，还实现了显著的计算效率。
英文摘要：
Accurate and efficient multivariate time series (MTS) analysis is increasingly critical for a wide range of intelligent applications. Within this realm, Transformers have emerged as the predominant architecture due to their strong ability to capture pairwise dependencies. However, Transformer-based models suffer from quadratic computational complexity and high memory overhead, limiting their scalability and practical deployment in long-term and large-scale MTS modeling. Recently, Mamba has emerged as a promising linear-time alternative with high expressiveness. Nevertheless, directly applying vanilla Mamba to MTS remains suboptimal due to three key limitations: (i) the lack of explicit cross-variate modeling, (ii) difficulty in disentangling the entangled intra-series temporal dynamics and inter-series interactions, and (iii) insufficient modeling of latent time-lag interaction effects. These issues constrain its effectiveness across diverse MTS tasks. To address these challenges, we propose DeMa, a dual-path delay-aware Mamba backbone. DeMa preserves Mamba's linear-complexity advantage while substantially improving its suitability for MTS settings. Specifically, DeMa introduces three key innovations: (i) it decomposes the MTS into intra-series temporal dynamics and inter-series interactions; (ii) it develops a temporal path with a Mamba-SSD module to capture long-range dynamics within each individual series, enabling series-independent, parallel computation; and (iii) it designs a variate path with a Mamba-DALA module that integrates delay-aware linear attention to model cross-variate dependencies. Extensive experiments on five representative tasks, long- and short-term forecasting, data imputation, anomaly detection, and series classification, demonstrate that DeMa achieves state-of-the-art performance while delivering remarkable computational efficiency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
