QAGT-MLP: An Attention-Based Graph Transformer for Small and Large-Scale Quantum Error Mitigation

2025-11-05

AI Summary

Existing quantum error mitigation techniques suffer from trade-offs among accuracy, efficiency, and scalability: traditional approaches (e.g., extrapolation, quasi-probability cancellation) incur high calibration overhead, while learning-based methods lack generalizability to large-scale, deep quantum circuits. To address this, we propose an attention-based Graph Transformer model that encodes quantum circuits as gate-level graphs. Our method introduces a novel dual-path attention mechanism—integrating global graph structure with local light-cone contextual information—enabling efficient error correction without additional sampling resources. The architecture synergistically combines graph neural networks, self-attention, dual-path feature fusion, and a lightweight MLP, significantly improving both accuracy and robustness. Experiments on 100-qubit transverse-field Ising model (TFIM) circuits demonstrate superior mean error reduction and lower variance compared to state-of-the-art learning-based mitigators, validating its practical applicability for near-term noisy intermediate-scale quantum (NISQ) processors.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Noisy quantum devices demand error-mitigation techniques to be accurate yet simple and efficient in terms of number of shots and processing time. Many established approaches (e.g., extrapolation and quasi-probability cancellation) impose substantial execution or calibration overheads, while existing learning-based methods have difficulty scaling to large and deep circuits. In this research, we introduce QAGT-MLP: an attention-based graph transformer tailored for small- and large-scale quantum error mitigation (QEM). QAGT-MLP encodes each quantum circuit as a graph whose nodes represent gate instances and whose edges capture qubit connectivity and causal adjacency. A dual-path attention module extracts features around measured qubits at two scales or contexts: 1) graph-wide global structural context; and 2) fine-grained local lightcone context. These learned representations are concatenated with circuit-level descriptor features and the circuit noisy expected values, then they are passed to a lightweight MLP to predict the noise-mitigated values. On large-scale 100-qubit Trotterized 1D Transverse-Field Ising Models -- TFIM circuits -- the proposed QAGT-MLP outperformed state-of-the-art learning baselines in terms of mean error and error variability, demonstrating strong validity and applicability in real-world QEM scenarios under matched shot budgets. By using attention to fuse global structures with local lightcone neighborhoods, QAGT-MLP achieves high mitigation quality without the increasing noise scaling or resource demand required by classical QEM pipelines, while still offering a scalable and practical path to QEM in modern and future quantum workloads.

Problem

• Mitigating quantum errors in both small and large-scale circuits efficiently
• Overcoming execution overhead of classical methods and scalability limitations of learning approaches
• Achieving high error mitigation quality without increasing resource demands

Innovation

• Attention-based graph transformer for quantum error mitigation
• Dual-path attention module extracts global and local contexts
• Lightweight MLP predicts noise-mitigated values from learned representations