Capturing Evolution Genes for Time Series Data
Abstract
The modeling of time series is becoming increasingly critical in a wide variety of applications. Overall, data evolves by following different patterns, which are generally caused by different user behaviors. Given a time series, we define the evolution gene to capture the latent user behaviors and to describe how the behaviors lead to the generation of time series. In particular, we propose a uniform framework that recognizes different evolution genes of segments by learning a classifier, and adopt an adversarial generator to implement the evolution gene by estimating the segments' distribution. Experimental results based on a synthetic dataset and five real-world datasets show that our approach can not only achieve a good prediction results (e.g., averagely +10.56% in terms of F1), but is also able to provide explanations of the results.
Cite
@article{arxiv.1905.05004,
title = {Capturing Evolution Genes for Time Series Data},
author = {Wenjie Hu and Jianping Huang and Liang Wu and Yang Yang and Zongtao Liu and Zhanlin Sun and Bingshen Yao and Ke Chen},
journal= {arXiv preprint arXiv:1905.05004},
year = {2022}
}