Quantum Autoencoder for Multivariate Time Series Anomaly Detection

2025-04-24

AI Summary

This work addresses the challenge of anomaly detection in enterprise-scale, high-dimensional multivariate time series (e.g., SAP HANA Cloud telemetry logs). Methodologically, it introduces the first scalable semi-supervised quantum autoencoder (QAE) framework—extending QAEs beyond univariate settings—by integrating quantum circuit encoding, variational quantum circuits, temporal embedding, and reconstruction loss optimization to construct a low-parameter quantum model. Theoretical analysis and empirical evaluation on real-world SAP system data demonstrate that the framework achieves anomaly detection accuracy comparable to deep neural network autoencoders while reducing parameter count by one to two orders of magnitude, thereby enabling practical deployment. The key contribution lies in overcoming the fundamental limitation of existing QAEs—restricted to univariate time series—and establishing a novel, industrially viable paradigm for applying quantum machine learning to multivariate time-series analysis.

Technology Category

• Machine Learning: Quantum Machine Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Anomaly Detection (AD) defines the task of identifying observations or events that deviate from typical - or normal - patterns, a critical capability in IT security for recognizing incidents such as system misconfigurations, malware infections, or cyberattacks. In enterprise environments like SAP HANA Cloud systems, this task often involves monitoring high-dimensional, multivariate time series (MTS) derived from telemetry and log data. With the advent of quantum machine learning offering efficient calculations in high-dimensional latent spaces, many avenues open for dealing with such complex data. One approach is the Quantum Autoencoder (QAE), an emerging and promising method with potential for application in both data compression and AD. However, prior applications of QAEs to time series AD have been restricted to univariate data, limiting their relevance for real-world enterprise systems. In this work, we introduce a novel QAE-based framework designed specifically for MTS AD towards enterprise scale. We theoretically develop and experimentally validate the architecture, demonstrating that our QAE achieves performance competitive with neural-network-based autoencoders while requiring fewer trainable parameters. We evaluate our model on datasets that closely reflect SAP system telemetry and show that the proposed QAE is a viable and efficient alternative for semisupervised AD in real-world enterprise settings.

Problem

• Detects anomalies in multivariate time series data
• Applies quantum autoencoder for enterprise-scale systems
• Competes with neural networks using fewer parameters

Innovation

• Quantum Autoencoder for multivariate time series
• Fewer trainable parameters than neural networks
• Competitive performance in anomaly detection