Network of Tensor Time Series

by   Baoyu Jing, et al.

Co-evolving time series appears in a multitude of applications such as environmental monitoring, financial analysis, and smart transportation. This paper aims to address the following challenges, including (C1) how to incorporate explicit relationship networks of the time series; (C2) how to model the implicit relationship of the temporal dynamics. We propose a novel model called Network of Tensor Time Series, which is comprised of two modules, including Tensor Graph Convolutional Network (TGCN) and Tensor Recurrent Neural Network (TRNN). TGCN tackles the first challenge by generalizing Graph Convolutional Network (GCN) for flat graphs to tensor graphs, which captures the synergy between multiple graphs associated with the tensors. TRNN leverages tensor decomposition to model the implicit relationships among co-evolving time series. The experimental results on five real-world datasets demonstrate the efficacy of the proposed method.


Tensor Graph Convolutional Networks for Prediction on Dynamic Graphs

Many irregular domains such as social networks, financial transactions, ...

Temporal Graph Convolutional Networks for Automatic Seizure Detection

Seizure detection from EEGs is a challenging and time consuming clinical...

Anomaly Detection on Graph Time Series

In this paper, we use variational recurrent neural network to investigat...

Adaptive Graph Convolutional Network Framework for Multidimensional Time Series Prediction

In the real world, long sequence time-series forecasting (LSTF) is neede...

T- Hop: Tensor representation of paths in graph convolutional networks

We describe a method for encoding path information in graphs into a 3-d ...

Space-Time-Separable Graph Convolutional Network for Pose Forecasting

Human pose forecasting is a complex structured-data sequence-modelling t...

Implicit Copulas: An Overview

Implicit copulas are the most common copula choice for modeling dependen...