Moon: A Modality Conversion-based Efficient Multivariate Time Series Anomaly Detection

2025-10-02

AI Summary

To address three key challenges in multivariate time series (MTS) anomaly detection—strong threshold dependency, insufficient modeling of local temporal dependencies, and poor interpretability—this paper proposes Moon, a supervised multimodal framework. Methodologically, Moon introduces (1) a novel Multivariate Markov Transition Field (MV-MTF) to transform MTS into interpretable 2D images; (2) a parameter-sharing multimodal CNN that jointly learns from raw numerical sequences and MV-MTF images, thereby enhancing local pattern discrimination; and (3) SHAP-based fine-grained anomaly attribution for transparent, instance-level explanations. Extensive experiments on six real-world benchmark datasets demonstrate that Moon achieves an average 4% improvement in detection accuracy over state-of-the-art methods, up to 93% faster inference speed, and a 10.8% gain in explanation fidelity.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Multivariate time series (MTS) anomaly detection identifies abnormal patterns where each timestamp contains multiple variables. Existing MTS anomaly detection methods fall into three categories: reconstruction-based, prediction-based, and classifier-based methods. However, these methods face two key challenges: (1) Unsupervised learning methods, such as reconstruction-based and prediction-based methods, rely on error thresholds, which can lead to inaccuracies; (2) Semi-supervised methods mainly model normal data and often underuse anomaly labels, limiting detection of subtle anomalies;(3) Supervised learning methods, such as classifier-based approaches, often fail to capture local relationships, incur high computational costs, and are constrained by the scarcity of labeled data. To address these limitations, we propose Moon, a supervised modality conversion-based multivariate time series anomaly detection framework. Moon enhances the efficiency and accuracy of anomaly detection while providing detailed anomaly analysis reports. First, Moon introduces a novel multivariate Markov Transition Field (MV-MTF) technique to convert numeric time series data into image representations, capturing relationships across variables and timestamps. Since numeric data retains unique patterns that cannot be fully captured by image conversion alone, Moon employs a Multimodal-CNN to integrate numeric and image data through a feature fusion model with parameter sharing, enhancing training efficiency. Finally, a SHAP-based anomaly explainer identifies key variables contributing to anomalies, improving interpretability. Extensive experiments on six real-world MTS datasets demonstrate that Moon outperforms six state-of-the-art methods by up to 93% in efficiency, 4% in accuracy and, 10.8% in interpretation performance.

Problem

• Improving accuracy of unsupervised MTS anomaly detection methods
• Enhancing utilization of anomaly labels in semi-supervised learning
• Reducing computational costs in supervised MTS anomaly detection

Innovation

• Converts time series to images using MV-MTF
• Integrates numeric and image data via Multimodal-CNN
• Explains anomalies with SHAP-based interpretation method