English

QNet: A Quantum-native Sequence Encoder Architecture

Machine Learning 2023-08-29 v2

Abstract

This work proposes QNet, a novel sequence encoder model that entirely inferences on the quantum computer using a minimum number of qubits. Let nn and dd represent the length of the sequence and the embedding size, respectively. The dot-product attention mechanism requires a time complexity of O(n2d)O(n^2 \cdot d), while QNet has merely O(n+d)O(n+d) quantum circuit depth. In addition, we introduce ResQNet, a quantum-classical hybrid model composed of several QNet blocks linked by residual connections, as an isomorph Transformer Encoder. We evaluated our work on various natural language processing tasks, including text classification, rating score prediction, and named entity recognition. Our models exhibit compelling performance over classical state-of-the-art models with a thousand times fewer parameters. In summary, this work investigates the advantage of machine learning on near-term quantum computers in sequential data by experimenting with natural language processing tasks.

Keywords

Cite

@article{arxiv.2210.17262,
  title  = {QNet: A Quantum-native Sequence Encoder Architecture},
  author = {Wei Day and Hao-Sheng Chen and Min-Te Sun},
  journal= {arXiv preprint arXiv:2210.17262},
  year   = {2023}
}

Comments

QCE23: 2023 IEEE International Conference on Quantum Computing & Engineering