Few-Shot Cross-Device Transfer for Quantum Noise Modeling on Real Hardware

2026-04-27

AI Summary

This work addresses the challenge that quantum hardware noise is device-specific, hindering the cross-device generalization of error mitigation strategies. To overcome this limitation, the authors propose a transfer learning–based approach for cross-device noise modeling and correction: a residual neural network noise model pretrained on a source device is fine-tuned using only a minimal number of samples (K=20) from the target device. Experiments on real IBM quantum hardware demonstrate that, on the ibm_marrakesh device, this method reduces the KL divergence of the output distribution from 1.6706 to 1.1924 with just 20 samples, achieving a 28.6% improvement over zero-shot transfer and closing 34.9% of the performance gap. This result provides the first empirical validation of the feasibility of fine-tuning cross-device noise models under extremely low-sample conditions.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

In the noisy intermediate-scale quantum (NISQ) regime, quantum devices contain hardware-specific noise sources which restrict device-invariant error mitigation strategies. We explore transfer learning approaches to apply noise models learned on one quantum device to a different device with the help of a small amount of data. We create a real-hardware dataset from two IBM quantum devices, ibm_fez (source) and ibm_marrakesh (target), comprising 170 noisy and ideal circuit output distributions, with device calibration features added. We train a residual neural network on the source device to map noisy to ideal outcomes. The zero-shot transfer test shows a KL divergence of 1.6706 (up from 0.3014), establishing device specificity. With K = 20 fine-tuning samples, KL drops to 1.1924 (28.6% improvement over zero-shot), recovering 34.9% of the gap between zero-shot and in-domain KL. Ablation studies reveal that the major cause of mismatches across devices is CX gate error, followed by readout error. The results show quantum noise can be learned and fine-tuned with minimal samples, and provide a plausible approach to cross-device quantum error mitigation.

Problem

• quantum noise modeling
• cross-device transfer
• few-shot learning
• NISQ
• error mitigation

Innovation

• few-shot transfer learning
• quantum noise modeling
• cross-device error mitigation
• NISQ devices
• residual neural network