Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time Series

Yicheng Luo, Bowen Zhang, Zhen Liu, Qianli Ma
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41494-41519, 2025.

Abstract

Multi-scale information is crucial for multivariate time series modeling. However, most existing time series multi-scale analysis methods treat all variables in the same manner, making them unsuitable for Irregular Multivariate Time Series (IMTS), where variables have distinct origin scales/sampling rates. To fill this gap, we propose Hi-Patch, a hierarchical patch graph network. Hi-Patch encodes each observation as a node, represents and captures local temporal and inter-variable dependencies of densely sampled variables through an intra-patch graph layer, and obtains patch-level nodes through aggregation. These nodes are then updated and re-aggregated through a stack of inter-patch graph layers, where several scale-specific graph networks progressively extract more global temporal and inter-variable features of both sparsely and densely sampled variables under specific scales. The output of the last layer is fed into task-specific decoders to adapt to different downstream tasks. Experiments on 8 datasets demonstrate that Hi-Patch outperforms state-of-the-art models in IMTS forecasting and classification tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-luo25r, title = {Hi-Patch: Hierarchical Patch {GNN} for Irregular Multivariate Time Series}, author = {Luo, Yicheng and Zhang, Bowen and Liu, Zhen and Ma, Qianli}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {41494--41519}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/luo25r/luo25r.pdf}, url = {https://proceedings.mlr.press/v267/luo25r.html}, abstract = {Multi-scale information is crucial for multivariate time series modeling. However, most existing time series multi-scale analysis methods treat all variables in the same manner, making them unsuitable for Irregular Multivariate Time Series (IMTS), where variables have distinct origin scales/sampling rates. To fill this gap, we propose Hi-Patch, a hierarchical patch graph network. Hi-Patch encodes each observation as a node, represents and captures local temporal and inter-variable dependencies of densely sampled variables through an intra-patch graph layer, and obtains patch-level nodes through aggregation. These nodes are then updated and re-aggregated through a stack of inter-patch graph layers, where several scale-specific graph networks progressively extract more global temporal and inter-variable features of both sparsely and densely sampled variables under specific scales. The output of the last layer is fed into task-specific decoders to adapt to different downstream tasks. Experiments on 8 datasets demonstrate that Hi-Patch outperforms state-of-the-art models in IMTS forecasting and classification tasks.} }
Endnote
%0 Conference Paper %T Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time Series %A Yicheng Luo %A Bowen Zhang %A Zhen Liu %A Qianli Ma %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-luo25r %I PMLR %P 41494--41519 %U https://proceedings.mlr.press/v267/luo25r.html %V 267 %X Multi-scale information is crucial for multivariate time series modeling. However, most existing time series multi-scale analysis methods treat all variables in the same manner, making them unsuitable for Irregular Multivariate Time Series (IMTS), where variables have distinct origin scales/sampling rates. To fill this gap, we propose Hi-Patch, a hierarchical patch graph network. Hi-Patch encodes each observation as a node, represents and captures local temporal and inter-variable dependencies of densely sampled variables through an intra-patch graph layer, and obtains patch-level nodes through aggregation. These nodes are then updated and re-aggregated through a stack of inter-patch graph layers, where several scale-specific graph networks progressively extract more global temporal and inter-variable features of both sparsely and densely sampled variables under specific scales. The output of the last layer is fed into task-specific decoders to adapt to different downstream tasks. Experiments on 8 datasets demonstrate that Hi-Patch outperforms state-of-the-art models in IMTS forecasting and classification tasks.
APA
Luo, Y., Zhang, B., Liu, Z. & Ma, Q.. (2025). Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time Series. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:41494-41519 Available from https://proceedings.mlr.press/v267/luo25r.html.

Related Material