Multivariate Time Series Classification with Hierarchical Variational Graph Pooling

TL;DR

This paper introduces MTPool, a hierarchical graph pooling framework that converts multivariate time series into graphs, enabling better spatial-temporal feature extraction and outperforming existing methods in classification accuracy.

Contribution

The paper proposes a novel hierarchical graph pooling method for multivariate time series classification that captures pairwise variable dependencies and aggregates data hierarchically.

Findings

MTPool outperforms state-of-the-art methods on ten benchmark datasets.

The framework effectively captures spatial-temporal dependencies in multivariate time series.

Hierarchical pooling improves the global representation of multivariate data.

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.