TodyNet: Temporal Dynamic Graph Neural Network for Multivariate Time Series Classification
This work addresses the challenge of capturing dynamic dependencies in multivariate time series for improved classification accuracy, which is an incremental advancement in the domain of time series analysis.
The authors tackled the problem of multivariate time series classification by proposing TodyNet, a temporal dynamic graph neural network that extracts hidden spatio-temporal dependencies without predefined graph structures, and it outperformed existing deep learning-based methods on 26 UEA benchmark datasets.
Multivariate time series classification (MTSC) is an important data mining task, which can be effectively solved by popular deep learning technology. Unfortunately, the existing deep learning-based methods neglect the hidden dependencies in different dimensions and also rarely consider the unique dynamic features of time series, which lack sufficient feature extraction capability to obtain satisfactory classification accuracy. To address this problem, we propose a novel temporal dynamic graph neural network (TodyNet) that can extract hidden spatio-temporal dependencies without undefined graph structure. It enables information flow among isolated but implicit interdependent variables and captures the associations between different time slots by dynamic graph mechanism, which further improves the classification performance of the model. Meanwhile, the hierarchical representations of graphs cannot be learned due to the limitation of GNNs. Thus, we also design a temporal graph pooling layer to obtain a global graph-level representation for graph learning with learnable temporal parameters. The dynamic graph, graph information propagation, and temporal convolution are jointly learned in an end-to-end framework. The experiments on 26 UEA benchmark datasets illustrate that the proposed TodyNet outperforms existing deep learning-based methods in the MTSC tasks.