NuwaTS: a Foundation Model Mending Every Incomplete Time Series
Published:
2024.8
Our contributions are as follows:
- We introduce a novel solution, NuwaTS, capable of performing missing data imputation tasks on any incomplete time series unseen during the training phase. To the best of our knowledge, this represents the pioneering attempt in this field.
- We present a ``plug-and-play’’ fine-tuning technique that seamlessly transforms a one-for-all model into a domain-specific model with minimal data and computational resources, all without modifying the model’s original weights.
- The one-for-all NuwaTS consistently outperforms domain-specific state-of-the-art methods in imputation tasks across nearly all missing rates. Moreover, fine-tuned NuwaTS can be extended to time series forecasting, where its forecasting results are comparable to or even better than existing domain-specific time series forecasting models.