Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer

TL;DR

This paper introduces a novel approach for general time series forecasting by learning unified representations through frequency-based decomposition and capturing domain-specific features for adaptive transfer, achieving state-of-the-art results.

Contribution

It proposes Decomposed Frequency Learning for unified representations and the Time Series Register for domain-specific features, enabling effective transfer across diverse forecasting scenarios.

Findings

State-of-the-art performance on seven benchmarks

Effective few-shot and zero-shot forecasting capabilities

Improved generalization across multiple domains

Abstract

With the growing availability of multi-domain time series data, there is an increasing demand for general forecasting models pre-trained on multi-source datasets to support diverse downstream prediction scenarios. Existing time series foundation models primarily focus on scaling up pre-training datasets and model sizes to enhance generalization performance. In this paper, we take a different approach by addressing two critical aspects of general forecasting models: (1) how to derive unified representations from heterogeneous multi-domain time series data, and (2) how to effectively capture domain-specific features to enable adaptive transfer across various downstream scenarios. To address the first aspect, we propose Decomposed Frequency Learning as the pre-training task, which leverages frequency-based masking and reconstruction to decompose coupled semantic information in time series, resulting in unified representations across domains. For the second aspect, we introduce the Time Series Register, which captures domain-specific representations during pre-training and enhances adaptive transferability to downstream tasks. Our model achieves the state-of-the-art forecasting performance on seven real-world benchmarks, demonstrating remarkable few-shot and zero-shot capabilities.