When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series

TL;DR

This paper introduces A2P, a novel framework for forecasting future anomalies in time series data, combining anomaly-aware forecasting and synthetic anomaly prompting to improve prediction accuracy.

Contribution

The paper presents a new approach, A2P, that effectively predicts future anomalies by learning anomaly relationships and using a learnable prompt pool, addressing limitations of existing methods.

Findings

A2P outperforms state-of-the-art methods on real-world datasets.

The framework accurately predicts future anomalies in diverse scenarios.

Synthetic anomaly prompting enhances anomaly detection robustness.

Abstract

Recently, forecasting future abnormal events has emerged as an important scenario to tackle real-world necessities. However, the solution of predicting specific future time points when anomalies will occur, known as Anomaly Prediction (AP), remains under-explored. Existing methods dealing with time series data fail in AP, focusing only on immediate anomalies or failing to provide precise predictions for future anomalies. To address the AP task, we propose a novel framework called Anomaly to Prompt (A2P), comprised of Anomaly-Aware Forecasting (AAF) and Synthetic Anomaly Prompting (SAP). To enable the forecasting model to forecast abnormal time points, we adopt a strategy to learn the relationships of anomalies. For the robust detection of anomalies, our proposed SAP introduces a learnable Anomaly Prompt Pool (APP) that simulates diverse anomaly patterns using signal adaptive prompt. Comprehensive experiments on multiple real-world datasets demonstrate the superiority of A2P over state-of-the-art methods, showcasing its ability to predict future anomalies. Our implementation code is available at https://github.com/KU-VGI/AP.