A regularization method for quantum neural networks using data symmetry

Leveraging data symmetries has recently become a key strategy in quantum neural networks (QNNs) to improve training efficiency. In this study, we propose a symmetry-informed regularization method for QNNs based on an input density matrix. By introducing a penalty term that encourages the model to align with data symmetry, our method enables improved training speed. This symmetry-based regularization is simple to implement and does not require an explicitly specified symmetry group, although it requires access to training samples or to the input distribution from which an empirical or theoretical input density matrix can be constructed. We evaluate the method through numerical experiments on both classification tasks and quantum generative adversarial networks. In the small-scale classification experiments, the regularizer produced modest improvements in early-stage convergence and test loss. Our findings highlight the potential of symmetry-aware regularization in enhancing the performance of QML models.