The dilemma of quantum neural networks
This work highlights a critical limitation for researchers in quantum machine learning, showing that current QNNs are incremental and not yet practical for real-world applications.
The paper investigates whether quantum neural networks (QNNs) maintain advantages over classical models on real-world tasks, finding through systematic experiments that current QNNs fail to provide any benefit due to poor generalization and insensitivity to regularization.
The core of quantum machine learning is to devise quantum models with good trainability and low generalization error bound than their classical counterparts to ensure better reliability and interpretability. Recent studies confirmed that quantum neural networks (QNNs) have the ability to achieve this goal on specific datasets. With this regard, it is of great importance to understand whether these advantages are still preserved on real-world tasks. Through systematic numerical experiments, we empirically observe that current QNNs fail to provide any benefit over classical learning models. Concretely, our results deliver two key messages. First, QNNs suffer from the severely limited effective model capacity, which incurs poor generalization on real-world datasets. Second, the trainability of QNNs is insensitive to regularization techniques, which sharply contrasts with the classical scenario. These empirical results force us to rethink the role of current QNNs and to design novel protocols for solving real-world problems with quantum advantages.