MuSiCNet：一种用于不规则采样多元时间序列分析的渐进式由粗到细框架
MuSiCNet: A Gradual Coarse-to-Fine Framework for Irregularly Sampled Multivariate Time Series Analysis
AI总结：
针对不规则采样多元时间序列，本文提出由粗到细的多尺度多相关注意力框架MuSiCNet，通过尺度内注意力与相关建模、跨尺度对比和重建校正，在三类任务上达到SOTA竞争力。
摘要：
不规则采样多元时间序列（ISMTS）在现实中普遍存在。大多数现有方法将ISMTS视为带有缺失值的同步规则采样时间序列，忽视了这种不规则性主要源于采样率的变化。本文提出一种新视角：不规则性在某种意义上本质上是相对的。通过人为地将采样率从低到高设定，不规则采样时间序列可以被转换为一个由粗到细、分层的相对规则时间序列集合。我们观察到，额外的粗粒度相对规则序列不仅在一定程度上缓解了不规则采样带来的挑战，还融入了宽视角的时间信息，因此可作为表示学习的宝贵资产。为此，遵循“先见全局，再究细节”的学习理念，我们提出多尺度与多相关性注意力网络（Multi-Scale and Multi-Correlation Attention Network，MuSiCNet），结合多个尺度迭代细化ISMTS表示。具体而言，在每个尺度内，我们探索时间注意力和频率相关矩阵，以聚合序列内和序列间信息，自然地以更丰富、更内在的细节提升表示质量。而在相邻尺度之间，我们采用包含对比学习和重建结果调整的表示校正方法，以进一步提高表示一致性。MuSiCNet是一个ISMTS分析框架，在分类、插值和预测三项主流任务上持续具备与SOTA竞争的能力。
英文摘要：
Irregularly sampled multivariate time series (ISMTS) are prevalent in reality. Most existing methods treat ISMTS as synchronized regularly sampled time series with missing values, neglecting that the irregularities are primarily attributed to variations in sampling rates. In this paper, we introduce a novel perspective that irregularity is essentially relative in some senses. With sampling rates artificially determined from low to high, an irregularly sampled time series can be transformed into a hierarchical set of relatively regular time series from coarse to fine. We observe that additional coarse-grained relatively regular series not only mitigate the irregularly sampled challenges to some extent but also incorporate broad-view temporal information, thereby serving as a valuable asset for representation learning. Therefore, following the philosophy of learning that Seeing the big picture first, then delving into the details, we present the Multi-Scale and Multi-Correlation Attention Network (MuSiCNet) combining multiple scales to iteratively refine the ISMTS representation. Specifically, within each scale, we explore time attention and frequency correlation matrices to aggregate intra- and inter-series information, naturally enhancing the representation quality with richer and more intrinsic details. While across adjacent scales, we employ a representation rectification method containing contrastive learning and reconstruction results adjustment to further improve representation consistency. MuSiCNet is an ISMTS analysis framework that competitive with SOTA in three mainstream tasks consistently, including classification, interpolation, and forecasting.
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。
