Abstract

Time series modeling aims to capture the intrinsic factors underpinning observed data and its evolution. However, most existing studies ignore the evolutionary relations among these factors, which are what cause the combinatorial evolution of a given time series. For example, personal interests are intrinsic factors hidden behind users’ observable online shopping behaviors; consequently, a precise item recommendation depends not only on discovering the item-interest relationship, but also on an understanding of how user interests shift over time. In this paper, we propose to represent complex and dynamic relations among intrinsic factors of time series data by means of an evolutionary state graph structure. Accordingly, we propose the Evolutionary Graph Recurrent Networks (EGRN) to learn representations of these factors, along with the given time series, using a graph neural network framework. The learned representations can then be applied to time series classification tasks. From our experimental results, based on six real-world datasets, it can be seen that our approach clearly outperforms ten state-of-the-art baseline methods (eg+ 5% in terms of accuracy, and+ 15% in terms of F1 on average). In addition, we demonstrate that due to the graph structure’s improved interpretability, our method is also able to explain the logical causes of the predicted events. Code is available at https://github. com/VachelHU/ESGRN.

Date

2021

Authors

Wenjie Hu, Yang Yang, Zilong You, Zongtao Liu, Xiang Ren

Journal

WSDM 2021