Review: Quantum Architecture Search with Unsupervised Representation Learning

2024-01-21

AI Summary

Current quantum architecture search (QAS) methods for the Noisy Intermediate-Scale Quantum (NISQ) era suffer from heavy reliance on labeled data, high computational cost, and poor scalability. Method: This paper proposes an unsupervised representation learning–driven QAS framework. Its core innovations include: (1) a novel predictor-free paradigm that decouples representation learning from architecture search; (2) a graph neural network (GNN) encoder specifically designed for quantum circuit graphs to learn task-agnostic, general-purpose architectural representations; and (3) an efficient search strategy combining REINFORCE policy gradients with Bayesian optimization. Contribution/Results: The method significantly reduces the number of search iterations required. Evaluated on the IBM ibm_sherbrooke processor for MaxCut circuits, it demonstrates strong robustness—maintaining optimal performance even under realistic hardware noise. This work establishes a scalable, low-label-dependency pathway for large-scale quantum circuit optimization.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Quantum Machine Learning
• Constraint Satisfaction and Optimization: Search

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Unsupervised representation learning presents new opportunities for advancing Quantum Architecture Search (QAS) on Noisy Intermediate-Scale Quantum (NISQ) devices. QAS is designed to optimize quantum circuits for Variational Quantum Algorithms (VQAs). Most QAS algorithms tightly couple the search space and search algorithm, typically requiring the evaluation of numerous quantum circuits, resulting in high computational costs and limiting scalability to larger quantum circuits. Predictor-based QAS algorithms mitigate this issue by estimating circuit performance based on structure or embedding. However, these methods often demand time-intensive labeling to optimize gate parameters across many circuits, which is crucial for training accurate predictors. Inspired by the classical neural architecture search algorithm Arch2vec, we investigate the potential of unsupervised representation learning for QAS without relying on predictors. Our framework decouples unsupervised architecture representation learning from the search process, enabling the learned representations to be applied across various downstream tasks. Additionally, it integrates an improved quantum circuit graph encoding scheme, addressing the limitations of existing representations and enhancing search efficiency. This predictor-free approach removes the need for large labeled datasets. During the search, we employ REINFORCE and Bayesian Optimization to explore the latent representation space and compare their performance against baseline methods. We further validate our approach by executing the best-discovered MaxCut circuits on IBM's ibm_sherbrooke quantum processor, confirming that the architectures retain optimal performance even under real hardware noise. Our results demonstrate that the framework efficiently identifies high-performing quantum circuits with fewer search iterations.

Problem

• Optimizing quantum circuits for NISQ devices using unsupervised learning
• Reducing computational costs in Quantum Architecture Search
• Eliminating need for large labeled datasets in QAS

Innovation

• Unsupervised representation learning for QAS
• Improved quantum circuit graph encoding
• REINFORCE and Bayesian Optimization search