Irregularly Sampled Multivariate Time Series Classification: A Graph Learning Approach

To date, graph-based learning methods are proven to be effective for modeling spatial and structural dependencies. However, when applied to IS-MTS, they encounter three major challenges due to the complex data characteristics of IS-MTS: 1) variable time intervals between observations; 2) asynchronous time points across dimensions; and 3) a lack of prior knowledge of connectivity structure for message propagation. To fill these gaps, we propose a multivariate temporal graph network to coherently capture structural interactions, learn temporal dependencies, and handle challenging characteristics of IS-MTS data. Specifically, we first build a multivariate interaction module to handle frequent missing values and extract the graph structure relation automatically. Second, we design a novel adjacent graph propagation mechanism to aggregate the neighbor information from multistep snapshots. Third, we construct a masked temporal-aware attention module to explicitly consider the timestamp context and interval irregularity. Based on an extensive experimental evaluation, we demonstrate the superior performance of the proposed method.

Authors

• Zhen Wang
• Ting Jiang Megvii Technology Inc.
• Zenghui Xu
• Ji Zhang Alibaba Group
• Jianliang Gao

Keywords

• Time series analysis
• Data models
• Intelligent systems
• Graph theory
• Correlation
• Time measurement
• Predictive models
• Time Series
• Multivariate Time Series
• Time Series Classification
• Irregular Sampling
• Graph Learning Approach
• Time Interval
• Interpolation
• Electronic Health Records
• Structural Information
• Missing Values
• Climatological
• Long Short-term Memory
• Structural Connectivity
• Nodes In The Graph
• Prediction Task
• Graph Structure
• Temporal Dependencies
• Long Short-term Memory Network
• Graph Neural Networks
• Node Representations
• Node Embeddings
• Dependency Graph
• Weight Vector
• Node Feature Vectors
• Time Series Data
• Hidden State
• Intensive Care Unit
• Learned Weights
• Training Data
• Graphical Model