TiWeaver: Unified Temporal Dynamics Modeling via Contextual Patching
For practitioners in weather, finance, and health monitoring, TiWeaver provides a robust solution for forecasting on diverse time series with irregularities, but the improvement is incremental over existing methods.
TiWeaver proposes a unified framework for multivariate time series forecasting that adaptively handles diverse temporal dynamics and irregularities like missing values. It achieves state-of-the-art performance on 12 real-world datasets, outperforming existing methods by up to 25%.
Multivariate time series forecasting plays a critical role in real-world applications, including weather prediction, stock analysis, and health monitoring. Due to the diversity of data sources, time series exhibit diverse temporal dynamics, often accompanied by various irregularities such as missing values and non-uniform sampling frequencies. Such irregularities lead to complex and asynchronous temporal dependencies across channels. Thus, a single model with a fixed patching scheme often fails to adapt well to diverse multivariate time series, hindering accurate forecasting. In this paper, we propose TiWeaver, a unified framework designed to handle temporal dynamics and fine-grained inter-channel dependencies adaptively. Specifically, we introduce a Graph-Guided Adaptive Tokenizer (G$^2$AT) that divides time series into high contextually coherent patches by jointly considering temporal density and representation consistency. In addition, we propose a Fine-grained Asynchronous Dependency Extractor (FADE), which is designed to model fine-grained asynchronous inter-channel dependencies while incorporating long-term historical dependencies. We evaluate TiWeaver on 12 real-world time series datasets, where it achieves state-of-the-art performance, outperforming existing methods up to 25%. These results demonstrate its robustness and effectiveness across diverse domains and data characteristics.