Multivariate time-series classification with hierarchical variational graph pooling

DOI10.1016/J.NEUNET.2022.07.032MaRDI QIDQ6076713zbMATH OpenOpenAlexFDO

Authors Ziheng Duan, Haoyan Xu, Yueyang Wang, Yida Huang, Anni Ren, Zhongbin Xu, Yizhou Sun, Wei Wang

Publication date 17 October 2023

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2010.05649

zbMATH Keywords

graph classificationgraph neural networksgraph poolingmultivariate time series classification

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Learning and adaptive systems in artificial intelligence (68T05)

Abstract: 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.

Recommendations

• Learning a symbolic representation for multivariate time series classification
• The great multivariate time series classification bake off: a review and experimental evaluation of recent algorithmic advances
• A cycle deep belief network model for multivariate time series classification
• A deep multi-task representation learning method for time series classification and retrieval
• A multivariate time series classification based on \(\mu \sigma\)-DWC feature and tree-structured M-SVM

Cites work

• Bayesian common spatial patterns for multi-subject EEG classification
• Early classification of time series using multi-objective optimization techniques
• Visualizing data using t-SNE

Cited in

(4)

• A dual-topological graph memory network for anti-noise multivariate time series forecasting
• Multi-task transfer learning for timescale graphical event models
• Learning multivariate shapelets with multi-layer neural networks for interpretable time-series classification
• Learning local directed acyclic graphs based on multivariate time series data

This page was built for publication: Multivariate time-series classification with hierarchical variational graph pooling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6076713)