Abstract
Irregular multivariate time series forecasting is a challenging yet important problem in real-world applications, where observations are often irregularly sampled and asynchronously recorded across variables. Existing time series foundation models are mostly built on regularly sampled sequences, making them difficult to generalize to irregular time intervals and asynchronous cross-variable dependencies. To address these challenges, we propose QiYao-I, a manifold based foundation model for irregular multivariate time series forecasting. Specifically, we introduce a novel sampling-conditioned temporal manifold attention mechanism that maps real timestamps into a learnable temporal manifold feature space and injects temporal manifold biases into attention layers, enabling the model to capture both irregular time intervals and local sampling structures. Further, we propose a dynamic variable interaction mechanism with frequency awareness. It selectively performs cross-variable message passing under asynchronous observations. Extensive experiments on real-world irregular multivariate forecasting benchmarks demonstrate that QiYao-I achieves superior performance compared with both time series foundation models and end-to-end irregular forecasting models, showing strong generalization ability in zero-shot and few-shot settings.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Wang, L., Zhang, R., Zhao, K., Shu, Y., Rao, Z., Wang, M., Li, Y., Yang, B., & Guo, C. (2026). QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting. https://omanscience.com/en/articles/qiyao-i-a-manifold-based-foundation-model-for-irregular-multivariate-time-series-forecasting
MLA 9
Wang, Linfeng, et al. "QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting." https://omanscience.com/en/articles/qiyao-i-a-manifold-based-foundation-model-for-irregular-multivariate-time-series-forecasting.
Chicago (author–date)
Wang, Linfeng, Ruitong Zhang, Kai Zhao, Yang Shu, Zhongwen Rao, Meng Wang, Yijie Li, Bin Yang, and Chenjun Guo. 2026. "QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting." https://omanscience.com/en/articles/qiyao-i-a-manifold-based-foundation-model-for-irregular-multivariate-time-series-forecasting.
Harvard
Wang, L., Zhang, R., Zhao, K., Shu, Y., Rao, Z., Wang, M., Li, Y., Yang, B. and Guo, C. (2026) 'QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting', Available at: https://omanscience.com/en/articles/qiyao-i-a-manifold-based-foundation-model-for-irregular-multivariate-time-series-forecasting.
Vancouver
Wang L, Zhang R, Zhao K, Shu Y, Rao Z, Wang M, et al. QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting. https://omanscience.com/en/articles/qiyao-i-a-manifold-based-foundation-model-for-irregular-multivariate-time-series-forecasting
IEEE
L. Wang, R. Zhang, K. Zhao, Y. Shu, Z. Rao, M. Wang, Y. Li, B. Yang, and C. Guo, "QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting," https://omanscience.com/en/articles/qiyao-i-a-manifold-based-foundation-model-for-irregular-multivariate-time-series-forecasting.