Quantum-Inspired Neural Network with Runge-Kutta Method
DOI:
https://doi.org/10.1609/aaai.v38i16.29753Keywords:
NLP: Learning & Optimization for NLP, NLP: Language Grounding & Multi-modal NLPAbstract
In recent years, researchers have developed novel Quantum-Inspired Neural Network (QINN) frameworks for the Natural Language Processing (NLP) tasks, inspired by the theoretical investigations of quantum cognition. However, we have found that the training efficiency of QINNs is significantly lower than that of classical networks. We analyze the unitary transformation modules of existing QINNs based on the time displacement symmetry of quantum mechanics and discover that they are resembling a mathematical form similar to the first-order Euler method. The high truncation error associated with Euler method affects the training efficiency of QINNs. In order to enhance the training efficiency of QINNs, we generalize QINNs' unitary transformation modules to the Quantum-like high-order Runge-Kutta methods (QRKs). Moreover, we present the results of experiments on conversation emotion recognition and text classification tasks to validate the effectiveness of the proposed approach.Downloads
Published
2024-03-24
How to Cite
Fan, Z., Zhang, J., Zhang, P., Lin, Q., & Gao, H. (2024). Quantum-Inspired Neural Network with Runge-Kutta Method. Proceedings of the AAAI Conference on Artificial Intelligence, 38(16), 17977-17984. https://doi.org/10.1609/aaai.v38i16.29753
Issue
Section
AAAI Technical Track on Natural Language Processing I