arXiv 2505.038252025-05-15cs.LGcs.AI

智能增强对比张量分解：赋能低数据环境下的多维时间序列分类

Intelligently Augmented Contrastive Tensor Factorization: Empowering Multi-dimensional Time Series Classification in Low-Data Environments

Engineering Product Development Singapore University of Technology and Design（新加坡科技与设计大学工程产品开发学院）；School of Automation Chongqing University（重庆大学自动化学院）；Institute for Infocomm Research Agency for Science, Technology and Research（信息与通信研究所）；School of Electrical and Electronics Engineering Nanyang Technological University（南洋理工大学电子与电气工程学院）

Anushiya Arunan, Yan Qin, Xiaoli Li, Yuen Chau

备注：: Accepted in Expert Systems with Applications (DOI:https://doi.org/10.1016/j.eswa.2025.127889)
DOI：: 10.1016/j.eswa.2025.127889

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对低数据环境下多维时间序列分类中深度学习易过拟合的问题，提出ITA-CTF框架，通过智能增强模块生成有效增强样本结合带对比损失的张量分解学习表征，在5个任务上最高提升18.7%的性能。

摘要：

来自真实世界系统的多维时间序列分类需要对跨维度依赖、类内变化等复杂特征进行细粒度学习，而这一切都面临着训练数据可用性低的实际挑战。然而，由于模型过拟合，标准深度学习（DL）难以在低数据环境中学习到具有泛化性的特征。我们提出了一种通用且数据高效的框架——智能增强对比张量分解（Intelligently Augmented Contrastive Tensor Factorization, ITA-CTF），用于从多维时间序列中学习有效表征。CTF模块学习时间序列的核心解释组件（如传感器因子、时间因子），更重要的是学习它们的联合依赖关系。值得注意的是，与标准张量分解（TF）不同，CTF模块引入了一种新的对比损失优化方法，将相似性学习和类别感知引入到学习到的表征中，以提升分类性能。为了强化这种对比学习，前置的ITA模块会生成有针对性且信息丰富的增强样本，这些样本既能凸显原始数据中真实的类内模式，又能保留类别属性。这一过程通过动态采样一个“软”类别原型来引导每个查询数据样本的变形实现，最终生成的增强样本是“软”类别原型与查询样本之间智能的模式混合结果。这些增强样本使得CTF模块即使在原始训练数据有限的情况下，也能识别复杂的类内变化，并挖掘出不变的类别属性以实现准确的分类性能。我们在五个不同的分类任务上对所提方法进行了全面评估。与标准TF和若干深度学习基准方法相比，该方法取得了最高达18.7%的显著性能提升。

英文摘要：

Classification of multi-dimensional time series from real-world systems require fine-grained learning of complex features such as cross-dimensional dependencies and intra-class variations-all under the practical challenge of low training data availability. However, standard deep learning (DL) struggles to learn generalizable features in low-data environments due to model overfitting. We propose a versatile yet data-efficient framework, Intelligently Augmented Contrastive Tensor Factorization (ITA-CTF), to learn effective representations from multi-dimensional time series. The CTF module learns core explanatory components of the time series (e.g., sensor factors, temporal factors), and importantly, their joint dependencies. Notably, unlike standard tensor factorization (TF), the CTF module incorporates a new contrastive loss optimization to induce similarity learning and class-awareness into the learnt representations for better classification performance. To strengthen this contrastive learning, the preceding ITA module generates targeted but informative augmentations that highlight realistic intra-class patterns in the original data, while preserving class-wise properties. This is achieved by dynamically sampling a "soft" class prototype to guide the warping of each query data sample, which results in an augmentation that is intelligently pattern-mixed between the "soft" class prototype and the query sample. These augmentations enable the CTF module to recognize complex intra-class variations despite the limited original training data, and seek out invariant class-wise properties for accurate classification performance. The proposed method is comprehensively evaluated on five different classification tasks. Compared to standard TF and several DL benchmarks, notable performance improvements up to 18.7% were achieved.

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。