期刊
NEURAL NETWORKS
卷 154, 期 -, 页码 481-490出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2022.07.032
关键词
Multivariate time series classification; Graph neural networks; Graph pooling; Graph classification
资金
- National Key Research and Development Program of China [2019YFB2102600]
- National Natural Science Foundation of China [62002035]
- Natural Science Foundation of Chongqing, China [cstc2020jcyj-bshX0034]
Multivariate time-series classification (MTSC) has gained considerable attention in recent years. Existing deep-learning-based techniques focus on the temporal dependency of a single time series. This study proposes a novel graph-pooling-based framework, MTPool, to address the limitations of existing methods. MTPool combines graph neural networks and variational graph pooling to achieve global graph representation learning and graph coarsening.
In recent years, multivariate time-series classification (MTSC) has attracted considerable attention owing to the advancement of sensing technology. Existing deep-learning-based MTSC techniques, which mostly rely on convolutional or recurrent neural networks, focus primarily on the temporal dependency of a single time series. Based on this, complex pairwise dependencies among multivariate variables can be better described using advanced graph methods, where each variable is regarded as a node in the graph, and their dependencies are regarded as edges. Furthermore, current spatial- temporal modeling (e.g., graph classification) methodologies based on graph neural networks (GNNs) are inherently flat and cannot hierarchically aggregate node information. To address these limitations, we propose a novel graph-pooling-based framework, MTPool, to obtain an expressive global representation of MTS. We first convert MTS slices into graphs using the interactions of variables via a graph structure learning module and obtain the spatial-temporal graph node features via a temporal convolutional module. To obtain global graph-level representation, we design an encoder-decoder -based variational graph pooling module to create adaptive centroids for cluster assignments. Then, we com-bine 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. Finally, a differentiable classifier uses this coarsened representation to obtain the final predicted class. Experiments on ten benchmark datasets showed that MTPool outperforms state-of-the-art strategies in the MTSC task. (C) 2022 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据