ForecastGrapher: Redefining Multivariate Time Series Forecasting with Graph Neural Networks

no code implementations • 28 May 2024 • Wanlin Cai, Kun Wang, Hao Wu, Xiaoxu Chen, Yuankai Wu

The challenge of effectively learning inter-series correlations for multivariate time series forecasting remains a substantial and unresolved problem.

NuwaTS: a Foundation Model Mending Every Incomplete Time Series

1 code implementation • 24 May 2024 • Jinguo Cheng, Chunwei Yang, Wanlin Cai, Yuxuan Liang, Yuankai Wu

By combining this contrastive loss with the missing data imputation task, we train PLMs to obtain a one-for-all imputation model.

MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecasting

1 code implementation • 31 Dec 2023 • Wanlin Cai, Yuxuan Liang, Xianggen Liu, Jianshuai Feng, Yuankai Wu

To bridge this gap, this paper introduces MSGNet, an advanced deep learning model designed to capture the varying inter-series correlations across multiple time scales using frequency domain analysis and adaptive graph convolution.

Multivariate Time Series Forecasting Time Series