Anomaly Detection on Graph Time Series

TL;DR

This paper introduces a variational recurrent neural network that combines RNNs, graph convolutional networks, and external feature integration for effective anomaly detection in graph time series data, demonstrated on traffic flow datasets.

Contribution

The paper presents a novel model integrating RNNs, GCNs, and external factors for anomaly detection in graph time series, with an extendable online detection capability.

Findings

Effective anomaly detection on traffic data

Model extension to online detection

Incorporation of external factors improves accuracy

Abstract

In this paper, we use variational recurrent neural network to investigate the anomaly detection problem on graph time series. The temporal correlation is modeled by the combination of recurrent neural network (RNN) and variational inference (VI), while the spatial information is captured by the graph convolutional network. In order to incorporate external factors, we use feature extractor to augment the transition of latent variables, which can learn the influence of external factors. With the target function as accumulative ELBO, it is easy to extend this model to on-line method. The experimental study on traffic flow data shows the detection capability of the proposed method.