# Multivariate Time Series Classification with Hierarchical Variational Graph Pooling

arXiv: https://arxiv.org/abs/2010.05649 · HTML: https://mlsanity.com/paper/2010.05649/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2020.

## Built on by (most cited first, 12 of 12)

- [A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection](https://mlsanity.com/paper/2307.03759/) (2023)
- [Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey](https://mlsanity.com/paper/2302.02515/) (2023)
- [FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification](https://mlsanity.com/paper/2302.09818/) (2023)
- [TodyNet: Temporal Dynamic Graph Neural Network for Multivariate Time Series Classification](https://mlsanity.com/paper/2304.05078/) (2023)
- [Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values](https://mlsanity.com/paper/2401.05800/) (2024)
- [VSFormer: Value and Shape-Aware Transformer with Prior-Enhanced Self-Attention for Multivariate Time Series Classification](https://mlsanity.com/paper/2412.16515/) (2024)
- [DynaGraph: Interpretable Multi-Label Prediction from EHRs via Dynamic Graph Learning and Contrastive Augmentation](https://mlsanity.com/paper/2503.22257/) (2025)
- [TimeGraphs: Graph-based Temporal Reasoning](https://mlsanity.com/paper/2401.03134/) (2024)
- [SSHPool: The Separated Subgraph-based Hierarchical Pooling](https://mlsanity.com/paper/2403.16133/) (2024)
- [Introducing Diminutive Causal Structure into Graph Representation Learning](https://mlsanity.com/paper/2406.08709/) (2024)
- [A Systematic Study of Model Extraction Attacks on Graph Foundation Models](https://mlsanity.com/paper/2511.11912/) (2025)
- [GNN-XAR: A Graph Neural Network for Explainable Activity Recognition in Smart Homes](https://mlsanity.com/paper/2502.17999/) (2025)

## Abstract (arXiv)

With the advancement of sensing technology, multivariate time series classification (MTSC) has recently received considerable attention. Existing deep learning-based MTSC techniques, which mostly rely on convolutional or recurrent neural networks, are primarily concerned with the temporal dependency of single time series. As a result, they struggle to express pairwise dependencies among multivariate variables directly. Furthermore, current spatial-temporal modeling (e.g., graph classification) methodologies based on Graph Neural Networks (GNNs) are inherently flat and cannot aggregate hub data in a hierarchical manner. To address these limitations, we propose a novel graph pooling-based framework MTPool to obtain the expressive global representation of MTS. We first convert MTS slices to graphs by utilizing interactions of variables via graph structure learning module and attain the spatial-temporal graph node features via temporal convolutional module. To get global graph-level representation, we design an "encoder-decoder" based variational graph pooling module for creating adaptive centroids for cluster assignments. Then we combine GNNs and our proposed variational graph pooling layers for joint graph representation learning and graph coarsening, after which the graph is progressively coarsened to one node. At last, a differentiable classifier takes this coarsened representation to get the final predicted class. Experiments on ten benchmark datasets exhibit MTPool outperforms state-of-the-art strategies in the MTSC task.