A Wave is Worth 100 Words: Investigating Cross-Domain Transferability in Time Series

TL;DR

This paper introduces WQ4TS, a novel cross-domain pretraining method for time series that maps data into a spectral latent space, enabling effective transfer learning across diverse tasks and domains, achieving state-of-the-art results.

Contribution

The paper proposes a spectral latent space approach for cross-domain transfer in time series, compatible with existing models and effective in zero- and few-shot scenarios.

Findings

Achieves best performance on 87.5% of tasks.

Average metric improvement up to 34.7%.

Effective across forecasting, imputation, and classification.

Abstract

Time series analysis is a fundamental data mining task that supervised training methods based on empirical risk minimization have proven their effectiveness on specific tasks and datasets. However, the acquisition of well-annotated data is costly and a large amount of unlabeled series data is under-utilized. Due to distributional shifts across various domains and different patterns of interest across multiple tasks. The problem of cross-domain multi-task migration of time series remains a significant challenge. To address these problems, this paper proposes a novel cross-domain pretraining method based on Wave Quantization (termed as WQ4TS), which can be combined with any advanced time series model and applied to multiple downstream tasks. Specifically, we transfer the time series data from different domains into a common spectral latent space, and enable the model to learn the temporal pattern knowledge of different domains directly from the common space and utilize it for the inference of downstream tasks, thereby mitigating the challenge of heterogeneous cross-domains migration. The establishment of spectral latent space brings at least three benefits, cross-domain migration capability thus adapting to zero- and few-shot scenarios without relying on priori knowledge of the dataset, general compatible cross-domain migration framework without changing the existing model structure, and robust modeling capability thus achieving SOTA results in multiple downstream tasks. To demonstrate the effectiveness of the proposed approach, we conduct extensive experiments including three important tasks: forecasting, imputation, and classification. And three common real-world data scenarios are simulated: full-data, few-shot, and zero-shot. The proposed WQ4TS achieves the best performance on 87.5% of all tasks, and the average improvement of the metrics on all the tasks is up to 34.7%.