Q-Fusion: Diffusing Quantum Circuits

2025-04-29

AI Summary

Current NISQ devices suffer from limited qubit counts and noisy gate operations, while quantum circuit design remains heavily reliant on expert intuition, resulting in low efficiency and scalability. Method: This paper proposes the first diffusion model–based Quantum Architecture Search (QAS) framework. It innovatively integrates the diffusion generative paradigm with LayerDAG graph-structured modeling and parameterized quantum circuit encoding to enable end-to-end, high-fidelity generation of syntactically and topologically valid circuits. Contribution/Results: Experiments demonstrate that our method achieves 100% circuit validity, significantly outperforming existing QAS baselines—including LLM-, RL-, and VAE-based approaches—in both fidelity and structural diversity. The framework establishes a novel, automated, and scalable paradigm for quantum algorithm design tailored to the NISQ era.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Computer Vision: Diffusion Models for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Quantum computing holds great potential for solving socially relevant and computationally complex problems. Furthermore, quantum machine learning (QML) promises to rapidly improve our current machine learning capabilities. However, current noisy intermediate-scale quantum (NISQ) devices are constrained by limitations in the number of qubits and gate counts, which hinder their full capabilities. Furthermore, the design of quantum algorithms remains a laborious task, requiring significant domain expertise and time. Quantum Architecture Search (QAS) aims to streamline this process by automatically generating novel quantum circuits, reducing the need for manual intervention. In this paper, we propose a diffusion-based algorithm leveraging the LayerDAG framework to generate new quantum circuits. This method contrasts with other approaches that utilize large language models (LLMs), reinforcement learning (RL), variational autoencoders (VAE), and similar techniques. Our results demonstrate that the proposed model consistently generates 100% valid quantum circuit outputs.

Problem

• Overcoming NISQ device qubit and gate count limitations
• Automating quantum circuit design to reduce manual effort
• Generating valid quantum circuits using diffusion-based methods

Innovation

• Diffusion-based algorithm for quantum circuits
• LayerDAG framework for circuit generation
• Ensures 100% valid quantum circuit outputs