Quantum Transfer Learning Shows Improved Robustness in Low-Data Regimes

TL;DR

This paper demonstrates that quantum models exhibit greater robustness and data efficiency than classical models in low-data transfer learning scenarios, maintaining more stable performance across various tasks.

Contribution

It provides the first systematic empirical comparison of quantum and classical models' robustness in low-data transfer learning settings.

Findings

Quantum models show less accuracy degradation with limited data.

Classical models achieve higher peak performance but are less robust.

Quantum models maintain stable performance across diverse transfer tasks.

Abstract

Transfer learning under limited data is a challenging setting, where models must adapt to new tasks with minimal supervision. Prior work has primarily focused on improving absolute accuracy in transfer learning. However, empirical evidence comparing quantum and classical models in realistic transfer learning settings remains limited, especially in low-data regimes. In this work, we systematically study the robustness of quantum models under reduced training data. We evaluate multiple quantum and classical architectures across diverse transfer tasks and retraining configurations, and quantify robustness using accuracy degradation and relative performance retention (RPR). Our results show that, although classical models often achieve higher peak performance, they exhibit significantly larger degradation when training data is limited. In contrast, quantum models maintain more stable performance across data regimes, indicating improved robustness and data efficiency. These findings provide empirical evidence that quantum models can offer improved robustness in low-resource transfer learning scenarios.