Learning Reduced Representations for Quantum Classifiers

2025-12-01

AI Summary

To address the challenge of adapting high-dimensional data to quantum machine learning, this paper proposes Sinkclass—a structured autoencoder designed to learn compact, quantum-compatible low-dimensional representations. We systematically evaluate six classical feature extraction methods and five autoencoder architectures on particle physics data, integrating each with a quantum support vector machine (QSVM) for binary classification. Experimental results demonstrate that embeddings generated by Sinkclass significantly enhance QSVM performance, yielding a 40% accuracy improvement over baseline approaches. This work constitutes the first effort to deeply co-design structured autoencoders with quantum classification pipelines, establishing a scalable, high-performance dimensionality reduction paradigm for quantum machine learning on scientific data. By enabling effective encoding of complex, real-world high-dimensional datasets into quantum-feasible latent spaces, our framework substantially extends the practical applicability of quantum algorithms beyond idealized benchmarks.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Data Compression

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Machine learning and data science for the Web

Abstract

Data sets that are specified by a large number of features are currently outside the area of applicability for quantum machine learning algorithms. An immediate solution to this impasse is the application of dimensionality reduction methods before passing the data to the quantum algorithm. We investigate six conventional feature extraction algorithms and five autoencoder-based dimensionality reduction models to a particle physics data set with 67 features. The reduced representations generated by these models are then used to train a quantum support vector machine for solving a binary classification problem: whether a Higgs boson is produced in proton collisions at the LHC. We show that the autoencoder methods learn a better lower-dimensional representation of the data, with the method we design, the Sinkclass autoencoder, performing 40% better than the baseline. The methods developed here open up the applicability of quantum machine learning to a larger array of data sets. Moreover, we provide a recipe for effective dimensionality reduction in this context.

Problem

• Reducing high-dimensional data for quantum classifiers
• Applying dimensionality reduction to particle physics datasets
• Enhancing quantum machine learning applicability via feature extraction

Innovation

• Autoencoder-based dimensionality reduction for quantum classifiers
• Sinkclass autoencoder improves quantum SVM performance by 40%
• Recipe for effective dimensionality reduction enabling quantum machine learning