Unsupervised Event Outlier Detection in Continuous Time

TL;DR

This paper introduces an unsupervised outlier detection method for continuous-time event sequences using a GAN-RL framework, enabling online detection of anomalies with improved accuracy over existing methods.

Contribution

It presents the first unsupervised outlier detection approach for event sequences based on GANs and reinforcement learning, capable of online anomaly detection.

Findings

Outperforms state-of-the-art outlier detection methods

Effective in online detection scenarios

Utilizes data augmentation via generator mistakes

Abstract

Event sequence data record the occurrences of events in continuous time. Event sequence forecasting based on temporal point processes (TPPs) has been extensively studied, but outlier or anomaly detection, especially without any supervision from humans, is still underexplored. In this work, we develop, to the best our knowledge, the first unsupervised outlier detection approach to detecting abnormal events. Our novel unsupervised outlier detection framework is based on ideas from generative adversarial networks (GANs) and reinforcement learning (RL). We train a 'generator' that corrects outliers in the data with a 'discriminator' that learns to discriminate the corrected data from the real data, which may contain outliers. A key insight is that if the generator made a mistake in the correction, it would generate anomalies that are different from the anomalies in the real data, so it serves as data augmentation for the discriminator learning. Different from typical GAN-based outlier detection approaches, our method employs the generator to detect outliers in an online manner. The experimental results show that our method can detect event outliers more accurately than the state-of-the-art approaches.