Efficient Hierarchical Contrastive Self-supervising Learning for Time Series Classification via Importance-aware Resolution Selection

TL;DR

This paper introduces an efficient hierarchical contrastive self-supervised learning method for time series classification that reduces computational costs by importance-aware resolution selection, maintaining high classification performance.

Contribution

It proposes a novel importance-aware resolution selection framework to improve training efficiency in hierarchical contrastive learning for long time series.

Findings

Significant reduction in training time.

Maintains high classification accuracy.

Effective for long time series data.

Abstract

Recently, there has been a significant advancement in designing Self-Supervised Learning (SSL) frameworks for time series data to reduce the dependency on data labels. Among these works, hierarchical contrastive learning-based SSL frameworks, which learn representations by contrasting data embeddings at multiple resolutions, have gained considerable attention. Due to their ability to gather more information, they exhibit better generalization in various downstream tasks. However, when the time series data length is significant long, the computational cost is often significantly higher than that of other SSL frameworks. In this paper, to address this challenge, we propose an efficient way to train hierarchical contrastive learning models. Inspired by the fact that each resolution's data embedding is highly dependent, we introduce importance-aware resolution selection based training framework to reduce the computational cost. In the experiment, we demonstrate that the proposed method significantly improves training time while preserving the original model's integrity in extensive time series classification performance evaluations. Our code could be found here, https://github.com/KEEBVIN/IARS