QNet:一种量子原生序列编码器架构
QNet: A Quantum-native Sequence Encoder Architecture
AI总结:
本研究提出量子原生序列编码器QNet及残差混合模型ResQNet,以更低的电路深度和千倍更少参数量,在多项自然语言处理任务上取得优于经典最优模型的性能,验证了近期量子机器学习处理序列数据的优势。
摘要:
本研究提出QNet,这是一种全新的序列编码器模型,可使用最少数量的量子比特完全在量子计算机上完成推理。设$n$和$d$分别代表序列长度和嵌入维度,点积注意力机制的时间复杂度为$O(n^2 \cdot d)$,而QNet的量子电路深度仅为$O(n+d)$。此外,我们提出了ResQNet,这是一种由多个通过残差连接相连的QNet模块组成的量子-经典混合模型,可作为同构Transformer Encoder(Transformer编码器)。我们在多种自然语言处理任务上对所提方法进行了评估,包括文本分类、评分预测和命名实体识别。我们的模型以少一千倍的参数量展现出优于经典SOTA(state-of-the-art,当前最优)模型的出色性能。综上,本研究通过自然语言处理任务实验,探究了近期量子计算机上机器学习在序列数据处理方面的优势。
英文摘要:
This work proposes QNet, a novel sequence encoder model that entirely inferences on the quantum computer using a minimum number of qubits. Let $n$ and $d$ represent the length of the sequence and the embedding size, respectively. The dot-product attention mechanism requires a time complexity of $O(n^2 \cdot d)$, while QNet has merely $O(n+d)$ 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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。