UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting
This work addresses the need for more flexible and efficient forecasting models across diverse domains like web technologies, though it appears incremental as it builds on existing unified model paradigms.
The paper tackles the problem of creating a unified model for cross-domain multivariate time series forecasting, addressing challenges like data disparities and domain confusion, and demonstrates improved state-of-the-art performance and zero-shot transferability in experiments.
Multivariate time series forecasting plays a pivotal role in contemporary web technologies. In contrast to conventional methods that involve creating dedicated models for specific time series application domains, this research advocates for a unified model paradigm that transcends domain boundaries. However, learning an effective cross-domain model presents the following challenges. First, various domains exhibit disparities in data characteristics, e.g., the number of variables, posing hurdles for existing models that impose inflexible constraints on these factors. Second, the model may encounter difficulties in distinguishing data from various domains, leading to suboptimal performance in our assessments. Third, the diverse convergence rates of time series domains can also result in compromised empirical performance. To address these issues, we propose UniTime for effective cross-domain time series learning. Concretely, UniTime can flexibly adapt to data with varying characteristics. It also uses domain instructions and a Language-TS Transformer to offer identification information and align two modalities. In addition, UniTime employs masking to alleviate domain convergence speed imbalance issues. Our extensive experiments demonstrate the effectiveness of UniTime in advancing state-of-the-art forecasting performance and zero-shot transferability.