Neural quantum support vector data description for one-class classification

2026-03-03

AI Summary

This work addresses one-class classification in high-dimensional, complex data by proposing NQSVDD, a classical-quantum hybrid framework that, for the first time, integrates trainable quantum data encoding and variational quantum circuits into this task. The method employs end-to-end optimization to jointly learn hierarchical representations from both classical neural networks and quantum modules, constructing a minimum-volume hyperspherical decision boundary in a compact latent space. Experimental results demonstrate that NQSVDD achieves or surpasses the AUC performance of classical Deep SVDD and existing quantum baselines across multiple benchmark datasets, while exhibiting high parameter efficiency and strong robustness to realistic noise.

Technology Category

Machine Learning: Quantum Machine LearningSearch and Optimization: Learning to SearchComputer Vision: Learning & Optimization for CV

Application Category

Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasetsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingGraph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

One-class classification (OCC) is a fundamental problem in machine learning with numerous applications, such as anomaly detection and quality control. With the increasing complexity and dimensionality of modern datasets, there is a growing demand for advanced OCC techniques with better expressivity and efficiency. We introduce Neural Quantum Support Vector Data Description (NQSVDD), a classical-quantum hybrid framework for OCC that performs end-to-end optimized hierarchical representation learning. NQSVDD integrates a classical neural network with trainable quantum data encoding and a variational quantum circuit, enabling the model to learn nonlinear feature transformations tailored to the OCC objective. The hybrid architecture maps input data into an intermediate high-dimensional feature space and subsequently projects it into a compact latent space defined through quantum measurements. Importantly, both the feature embedding and the latent representation are jointly optimized such that normal data form a compact cluster, for which a minimum-volume enclosing hypersphere provides an effective decision boundary. Experimental evaluations on benchmark datasets demonstrate that NQSVDD achieves competitive or superior AUC performance compared to classical Deep SVDD and quantum baselines, while maintaining parameter efficiency and robustness under realistic noise conditions.

Problem

• one-class classification
• anomaly detection
• quantum machine learning
• support vector data description
• high-dimensional data

Innovation

• Neural Quantum Hybrid
• One-Class Classification
• Variational Quantum Circuit
• Quantum Data Encoding
• Minimum-Volume Enclosing Hypersphere