Predictive Performance of Deep Quantum Data Re-uploading Models
This addresses a fundamental limitation for researchers in quantum machine learning, highlighting design implications to avoid performance pitfalls in quantum models.
The study tackled the problem of predictive performance degradation in deep quantum data re-uploading models, revealing that increasing encoding layers leads to near random-guessing accuracy on high-dimensional data, as validated by experiments on synthetic and real-world datasets.
Quantum machine learning models incorporating data re-uploading circuits have garnered significant attention due to their exceptional expressivity and trainability. However, their ability to generate accurate predictions on unseen data, referred to as the predictive performance, remains insufficiently investigated. This study reveals a fundamental limitation in predictive performance when deep encoding layers are employed within the data re-uploading model. Concretely, we theoretically demonstrate that when processing high-dimensional data with limited-qubit data re-uploading models, their predictive performance progressively degenerates to near random-guessing levels as the number of encoding layers increases. In this context, the repeated data uploading cannot mitigate the performance degradation. These findings are validated through experiments on both synthetic linearly separable datasets and real-world datasets. Our results demonstrate that when processing high-dimensional data, the quantum data re-uploading models should be designed with wider circuit architectures rather than deeper and narrower ones.