SEA++：基于多图的高阶传感器对齐用于多变量时间序列无监督域自适应
SEA++: Multi-Graph-based High-Order Sensor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation
- School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore（新加坡南洋理工大学电气与电子工程学院）
- School of Computer Science and Engineering, Nanyang Technological University, Singapore（新加坡南洋理工大学计算机科学与工程学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对多变量时间序列无监督域自适应（MTS-UDA）中传感器分布差异被忽略的问题，提出SEA和SEA++方法，通过内特征对齐和外特征对齐在局部和全局传感器级别减少域差异，并在公共数据集上达到最先进性能。
AI中文摘要：
无监督域自适应（UDA）方法通过最小化有标签源域和无标签目标域之间的域差异，在减少标签依赖方面取得了成功。然而，这些方法在处理多变量时间序列（MTS）数据时面临挑战。MTS数据通常由多个传感器组成，每个传感器都有其独特的分布。这一特性使得现有的UDA方法难以适应，这些方法主要关注对齐全局特征而忽略了传感器级别的分布差异，从而无法有效减少MTS数据的域差异。为了解决这个问题，一个实际的域自适应场景被形式化为多变量时间序列无监督域自适应（MTS-UDA）。在本文中，我们提出了用于MTS-UDA的传感器对齐（SEA），旨在减少局部和全局传感器级别的域差异。在局部传感器级别，我们设计了内特征对齐，跨域对齐传感器特征及其相关性。为了减少全局传感器级别的域差异，我们设计了外特征对齐，对全局传感器特征施加限制。我们通过增强内特征对齐进一步将SEA扩展为SEA++。具体而言，我们为传感器特征及其相关性引入了基于多图的高阶对齐。广泛的实证结果证明了我们的SEA和SEA++在公共MTS数据集上用于MTS-UDA的最先进性能。
英文摘要：
Unsupervised Domain Adaptation (UDA) methods have been successful in reducing label dependency by minimizing the domain discrepancy between a labeled source domain and an unlabeled target domain. However, these methods face challenges when dealing with Multivariate Time-Series (MTS) data. MTS data typically consist of multiple sensors, each with its own unique distribution. This characteristic makes it hard to adapt existing UDA methods, which mainly focus on aligning global features while overlooking the distribution discrepancies at the sensor level, to reduce domain discrepancies for MTS data. To address this issue, a practical domain adaptation scenario is formulated as Multivariate Time-Series Unsupervised Domain Adaptation (MTS-UDA). In this paper, we propose SEnsor Alignment (SEA) for MTS-UDA, aiming to reduce domain discrepancy at both the local and global sensor levels. At the local sensor level, we design endo-feature alignment, which aligns sensor features and their correlations across domains. To reduce domain discrepancy at the global sensor level, we design exo-feature alignment that enforces restrictions on global sensor features. We further extend SEA to SEA++ by enhancing the endo-feature alignment. Particularly, we incorporate multi-graph-based high-order alignment for both sensor features and their correlations. Extensive empirical results have demonstrated the state-of-the-art performance of our SEA and SEA++ on public MTS datasets for MTS-UDA.
