Backend-Aware Graph Learning for Denoising Outcome Distributions in Quantum Program Testing

2026-07-25

AI Summary

This work addresses the challenge of output distribution distortion in quantum programs caused by noise on Noisy Intermediate-Scale Quantum (NISQ) devices, which hampers reliable test outcome evaluation. To this end, the authors propose Q-BRIDGE, a novel method that jointly models the graph structure of transpiled quantum circuits and the physical characteristics of target quantum backends. By employing a graph Transformer to encode circuit topology and integrating empirical noise data via FiLM conditional layers, Q-BRIDGE generates denoised output distributions tailored for testing and verification. The approach supports both single-backend specialized and multi-backend generalizable modes. Extensive experiments across 23 IBM quantum backends and six circuit classes demonstrate that Q-BRIDGE substantially outperforms existing noise mitigation techniques, achieving defect detection precision of 93.97%–94.90% and recall of 82.50%–83.51%.

Abstract

Testing quantum programs on NISQ (Noisy Intermediate-Scale Quantum) backends is challenging because the noise disturbs outcome distributions and can affect pass/fail decisions. We present Q-BRIDGE, a graph learning-based approach that converts noisy observations into denoised distributions suitable for oracle-based verification. Q-BRIDGE uses a graph transformer architecture to encode a transpiled quantum circuit, capturing the characteristics of its gates and their connectivity; the physical backend information is encoded together with the logical structure of the circuit. An additional conditioning layer, based on FiLM (Feature-Wise Linear Modulation), takes the encoding as input and integrates noisy observations to produce denoised outcomes. We evaluate Q-BRIDGE on 23 IBM noise backends and 6 circuit families representative of practical workloads. In the first setting, we train a separate Q-BRIDGE model for each backend; in the second setting, we train a single general model shared across all backends. Across both settings, Q-BRIDGE outperforms the state-of-the-art baseline in noise mitigation by a large margin. In testing scenarios with noisy executions, Q-BRIDGE achieves 93.97%-94.90% precision and 82.50%-83.51% recall in detecting bug-induced test failures, significantly outperforming the state-of-the-art baseline. These results indicate that considering the graph structure of the transpiled circuits and the physical characteristics of specific quantum backends is a practical route to more reliable noise-aware quantum program testing.

Problem

• quantum program testing
• noise mitigation
• outcome distribution denoising
• NISQ backends
• oracle-based verification

Innovation

• graph transformer
• quantum program testing
• noise mitigation
• backend-aware learning
• FiLM conditioning