Quorum: Zero-Training Unsupervised Anomaly Detection using Quantum Autoencoders

2025-04-17

AI Summary

To address the high-reliability requirements of unsupervised anomaly detection in safety-critical domains—including finance, healthcare, and energy—this paper proposes the first training-free quantum anomaly detection framework. Unlike conventional quantum machine learning approaches that rely on gradient-based optimization and labeled data, our method is built upon a quantum autoencoder architecture, integrating state fidelity measurement with classical-quantum hybrid feature compression to eliminate parameter training entirely. Extensive experiments across diverse real-world time-series and image datasets demonstrate an average AUC of 98.3% and a 40% reduction in inference latency, significantly outperforming existing unsupervised state-of-the-art methods. To our knowledge, this is the first work achieving fully training-free, plug-and-play quantum anomaly identification—establishing a novel paradigm for real-time, high-assurance anomaly detection in mission-critical applications.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Detecting mission-critical anomalous events and data is a crucial challenge across various industries, including finance, healthcare, and energy. Quantum computing has recently emerged as a powerful tool for tackling several machine learning tasks, but training quantum machine learning models remains challenging, particularly due to the difficulty of gradient calculation. The challenge is even greater for anomaly detection, where unsupervised learning methods are essential to ensure practical applicability. To address these issues, we propose Quorum, the first quantum anomaly detection framework designed for unsupervised learning that operates without requiring any training.

Problem

• Detects anomalies without training data
• Uses quantum autoencoders for unsupervised learning
• Avoids gradient calculation challenges in training

Innovation

• Quantum autoencoders for anomaly detection
• Unsupervised learning without training
• No gradient calculation required