Heterogeneous Relationships of Subjects and Shapelets for Semi-supervised Multivariate Series Classification

2024-11-27

arXiv.org

AI Summary

To address the challenges of high-dimensional modeling and scarce labeled data in semi-supervised multivariate time series (MTS) classification, this paper proposes a subject–shape heterogeneous graph modeling framework. The method integrates sparse temporal representation, soft dynamic time warping (soft DTW) for similarity graph construction, learnable shapelet enhancement, and a two-level graph attention mechanism—enabling, for the first time, joint modeling of subject-level features and shapelet structures. Contrastive temporal self-attention is further employed to enhance discriminative representation learning. Extensive experiments on benchmark datasets—including HAR, sleep staging, and the UEA archive—demonstrate significant improvements over existing state-of-the-art methods, with robust performance even under extremely low labeling ratios. This work establishes a novel paradigm for semi-supervised MTS classification.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Multivariate time series (MTS) classification is widely applied in fields such as industry, healthcare, and finance, aiming to extract key features from complex time series data for accurate decision-making and prediction. However, existing methods for MTS often struggle due to the challenges of effectively modeling high-dimensional data and the lack of labeled data, resulting in poor classification performance. To address this issue, we propose a heterogeneous relationships of subjects and shapelets method for semi-supervised MTS classification. This method offers a novel perspective by integrating various types of additional information while capturing the relationships between them. Specifically, we first utilize a contrast temporal self-attention module to obtain sparse MTS representations, and then model the similarities between these representations using soft dynamic time warping to construct a similarity graph. Secondly, we learn the shapelets for different subject types, incorporating both the subject features and their shapelets as additional information to further refine the similarity graph, ultimately generating a heterogeneous graph. Finally, we use a dual level graph attention network to get prediction. Through this method, we successfully transform dataset into a heterogeneous graph, integrating multiple additional information and achieving precise semi-supervised node classification. Experiments on the Human Activity Recognition, sleep stage classification and University of East Anglia datasets demonstrate that our method outperforms current state-of-the-art methods in MTS classification tasks, validating its superiority.

Problem

• Addresses poor classification in multivariate time series due to high-dimensional data challenges
• Integrates subject features and shapelets to refine similarity graphs for better accuracy
• Improves semi-supervised classification by constructing heterogeneous graphs with additional information

Innovation

• Contrast temporal self-attention for sparse MTS
• Soft dynamic time warping for similarity graph
• Dual level graph attention network for prediction