QSAN: A Near-term Achievable Quantum Self-Attention Network

Abstract

A Quantum Self-Attention Network (QSAN) that can be achieved on near-term quantum devices is investigated. First, the theoretical basis of QSAN, a linearized and reversible Quantum Self-Attention Mechanism (QSAM) including Quantum Logic Similarity (QLS) and Quantum Bit Self-Attention Score Matrix (QBSASM), is explored to solve the storage problem of Self-Attention Mechanism (SAM) due to quadratic complexity. More importantly, QLS uses logical operations instead of inner product operations to enable QSAN to be fully deployed on quantum computers and meanwhile saves quantum bits by avoiding numerical operations, and QBSASM is a by-product generated with the evolution of QSAN, reflecting the output attention distribution in the form of a density matrix. Then, the framework and the quantum circuit of QSAN are designed with 9 execution steps and 5 special functional sub-modules, which can acquire QBSASM effectively in the intermediate process, as well as compressing the number of measurements. In addition, a quantum coordinate prototype is proposed to describe the mathematical connection between the control and output bits in order to realize programming and model optimization conveniently. Finally, a miniaturized experiment is implemented and it demonstrates that QSAN can be trained faster in the presence of quantum natural gradient descent method, as well as produce quantum characteristic attention distribution QBSASM. QSAN has great potential to be embedded in classical or quantum machine learning frameworks to lay the foundation for quantum enhanced Natural Language Processing (NLP).

Deep Learning for Marine Science

“…It can predict the bounding box coordinates and the corresponding confidence scores with one single network. There are numerous YOLO versions dedicated to operating on underwater images for detection of various objects such as starfish, shrimp, crab, scallop, and waterweed Zhao et al, 2022). Among these models, the recently proposed model, YOLOfish was designed for fish detection and is reported to be performing close to YOLOv4 model on two different public datasets (Muksit et al, 2022).…”

“…As deep learning techniques have developed, researchers have began to design neural networks for predicting weather elements (e.g., rainfall), which can well mine complex and intrinsic correlations, such as artificial neural networks (ANN) Feng et al (2016), convolutional neural networks (CNN) ; Ye et al (2021b); Patil et al (2021), long short-term memory networks (LSTM) Broni-Bedaiko et al (2019), convolutional long short-term memory networks (ConvLSTM) Mu et al (2019); He et al (2019); Gupta et al (2022), CNN-LSTM Zhou and Zhang (2022), graph neural networks (GNN) , recurrent neural network (RNN) Zhao et al (2022), transformer Ye et al (2021a) etc. Feng et al Feng et al (2016) propose two methods to predict the existence of ENSO, and the time evolution of ENSO scalar features, which provided a new prediction direction for predicting the occurrence for ENSO events.…”

“…The GNN was first used in for seasonal prediction, it predict the result in a longer lead time. Zhao et al Zhao et al (2022) designed an endto-end network, named Spatio-Temporal Semantic Network (STSNet), it provided a multiscale receptive domains across spatial and temporal dimensions. The significant breakthrough work is the CNN-based model designed by , which is proficient in predicting ENSO incidents for as long as 1.5 years, significantly higher than most existing methods.…”

Hybrid quantum-classical convolutional neural network for phytoplankton classification

“…Its success has led to its application in classifying plankton datasets (Baek et al, 2022;Dagtekin and Dethlefs, 2022;Kyathanahally et al, 2022;Shao et al, 2022). In the future, it will be intriguing to develop quantum visual transformer models based on the quantum selfattention mechanism (Li et al, 2022;Shi et al, 2023;Zhao et al, 2022), and explore their potential for phytoplankton classification.…”

Multi-scale Attention Convolutional Neural Network for time series classification

“…Similarly, Sipio et al [35] proposed a quantum-enhanced transformer model by replacing the linear transformations in the classical transformer model with a VQC. Zhao et al [36] constructed the quantum self-attention network (QSAN) model by introducing quantum logic similarity (QLS) and quantum bit selfattention score matrix (QBSASM). Afterwards, Zhao et al [37] combined quantum kernel methods with self-attention mechanisms to propose the quantum kernel selfattention network (QKSAN) model.…”