Cross-Domain Pre-training with Language Models for Transferable Time Series Representations

TL;DR

This paper introduces CrossTimeNet, a novel framework for cross-domain self-supervised pre-training of time series models, utilizing a tokenization module and corrupted token prediction to improve transferability across diverse domains.

Contribution

We propose CrossTimeNet, a new SSL framework with a time series tokenization module and corrupted token prediction, enabling effective cross-domain transfer learning for time series data.

Findings

CrossTimeNet outperforms existing methods in real-world time series classification tasks.

The tokenization module effectively converts raw data into informative tokens.

Predicting corrupted tokens enhances the model's ability to learn transferable features.

Abstract

Advancements in self-supervised pre-training (SSL) have significantly advanced the field of learning transferable time series representations, which can be very useful in enhancing the downstream task. Despite being effective, most existing works struggle to achieve cross-domain SSL pre-training, missing valuable opportunities to integrate patterns and features from different domains. The main challenge lies in the significant differences in the characteristics of time-series data across different domains, such as variations in the number of channels and temporal resolution scales. To address this challenge, we propose CrossTimeNet, a novel cross-domain SSL learning framework to learn transferable knowledge from various domains to largely benefit the target downstream task. One of the key characteristics of CrossTimeNet is the newly designed time series tokenization module, which could effectively convert the raw time series into a sequence of discrete tokens based on a reconstruction optimization process. Besides, we highlight that predicting a high proportion of corrupted tokens can be very helpful for extracting informative patterns across different domains during SSL pre-training, which has been largely overlooked in past years. Furthermore, unlike previous works, our work treats the pre-training language model (PLM) as the initialization of the encoder network, investigating the feasibility of transferring the knowledge learned by the PLM to the time series area. Through these efforts, the path to cross-domain pre-training of a generic time series model can be effectively paved. We conduct extensive experiments in a real-world scenario across various time series classification domains. The experimental results clearly confirm CrossTimeNet's superior performance.