Higher-order Cross-structural Embedding Model for Time Series Analysis

TL;DR

This paper introduces High-TS, a novel framework that jointly models temporal and spatial dependencies in time series data using multiscale Transformers, Topological Deep Learning, and contrastive learning, leading to improved performance.

Contribution

The paper presents a new higher-order cross-structural embedding model that effectively captures complex interactions in time series data, combining multiple advanced techniques.

Findings

High-TS outperforms existing methods in various tasks.

Model effectively captures higher-order interactions.

Contrastive learning enhances representation robustness.

Abstract

Time series analysis has gained significant attention due to its critical applications in diverse fields such as healthcare, finance, and sensor networks. The complexity and non-stationarity of time series make it challenging to capture the interaction patterns across different timestamps. Current approaches struggle to model higher-order interactions within time series, and focus on learning temporal or spatial dependencies separately, which limits performance in downstream tasks. To address these gaps, we propose Higher-order Cross-structural Embedding Model for Time Series (High-TS), a novel framework that jointly models both temporal and spatial perspectives by combining multiscale Transformer with Topological Deep Learning (TDL). Meanwhile, High-TS utilizes contrastive learning to integrate these two structures for generating robust and discriminative representations. Extensive experiments show that High-TS outperforms state-of-the-art methods in various time series tasks and demonstrate the importance of higher-order cross-structural information in improving model performance.