Capturing Temporal Components for Time Series Classification

TL;DR

This paper introduces a multi-scale, unsupervised segmentation and compositional representation learning approach for time series classification, improving generalization across different sequence lengths.

Contribution

It proposes a novel multi-scale change space method for unsupervised segmentation and a multi-task encoder for learning compositional representations, enhancing time series classification.

Findings

Effective segmentation of time series into statistically coherent components.

Competitive performance on unsupervised segmentation benchmarks.

Improved classification accuracy across various datasets.

Abstract

Analyzing sequential data is crucial in many domains, particularly due to the abundance of data collected from the Internet of Things paradigm. Time series classification, the task of categorizing sequential data, has gained prominence, with machine learning approaches demonstrating remarkable performance on public benchmark datasets. However, progress has primarily been in designing architectures for learning representations from raw data at fixed (or ideal) time scales, which can fail to generalize to longer sequences. This work introduces a \textit{compositional representation learning} approach trained on statistically coherent components extracted from sequential data. Based on a multi-scale change space, an unsupervised approach is proposed to segment the sequential data into chunks with similar statistical properties. A sequence-based encoder model is trained in a multi-task setting to learn compositional representations from these temporal components for time series classification. We demonstrate its effectiveness through extensive experiments on publicly available time series classification benchmarks. Evaluating the coherence of segmented components shows its competitive performance on the unsupervised segmentation task.