Precursor-of-Anomaly Detection for Irregular Time Series

TL;DR

This paper introduces a novel Precursor-of-Anomaly detection method that predicts future anomalies in irregular time series using a neural controlled differential equation-based neural network, outperforming existing baselines.

Contribution

The paper proposes a new PoA detection framework with a neural controlled differential equation model and multi-task learning, addressing future anomaly prediction in irregular time series.

Findings

Outperforms 17 baseline methods across 3 datasets.

Multi-task training improves detection accuracy.

Effective on both regular and irregular time series.

Abstract

Anomaly detection is an important field that aims to identify unexpected patterns or data points, and it is closely related to many real-world problems, particularly to applications in finance, manufacturing, cyber security, and so on. While anomaly detection has been studied extensively in various fields, detecting future anomalies before they occur remains an unexplored territory. In this paper, we present a novel type of anomaly detection, called Precursor-of-Anomaly (PoA) detection. Unlike conventional anomaly detection, which focuses on determining whether a given time series observation is an anomaly or not, PoA detection aims to detect future anomalies before they happen. To solve both problems at the same time, we present a neural controlled differential equation-based neural network and its multi-task learning algorithm. We conduct experiments using 17 baselines and 3 datasets, including regular and irregular time series, and demonstrate that our presented method outperforms the baselines in almost all cases. Our ablation studies also indicate that the multitasking training method significantly enhances the overall performance for both anomaly and PoA detection.