27 April 2023 in AVS Quantum Science
We develop and implement two realizations of quantum graph neural networks (QGNN), applied to the task of particle interaction simulation. The first QGNN is a speculative quantum-classical hybrid learning model that relies on the ability to directly utilize superposition states as classical information to propagate information between particles. The second is an implementable quantum-classical hybrid learning model that propagates particle information directly through the parameters of RX rotation gates. A classical graph neural network (CGNN) is also trained in the same task. Both the Speculative QGNN and CGNN act as controls against the Implementable QGNN. Comparison between classical and quantum models is based on the loss value and accuracy of each model. Overall, each model had a high learning efficiency, in which the loss value rapidly approached zero during training; however, each model was moderately inaccurate. Comparing performances, our results show that the Implementable QGNN has a potential advantage over the CGNN. Additionally, we show that a slight alteration in hyperparameters in the CGNN notably improves accuracy, suggesting that further fine tuning could mitigate the issue of moderate inaccuracy in each model.
1 December 2024 in AVS Quantum Science
Initiated by the authors, this erratum is written concerning the discovery of a misplaced unitary within the software implementation of the Implementable Quantum Graph Neural Network (QGNN) of the original paper. Analyzing this mistake's impact on the results, it is shown to be negligible, meaning that the results, analysis, and conclusion of the original paper remain valid. The misplacement of this unitary is found to be negligible due to it being a redundant feature in the Implementable QGNN, in addition to the parameterized quantum circuits employed being able to learn to a moderately effective degree by themselves; though, the unitaries that correspond to graph neural network algorithmic values utilized within the Implementable QGNN are still shown to be critical to the performance capability of this quantum machine learning model.