Quantum Complex-Valued Self-Attention Model

2025-03-24 · Fu Chen, Qinglin Zhao, Li Feng, Longfei Tang, Yangbin Lin, Haitao Huang

Self-attention has revolutionized classical machine learning, yet existing quantum self-attention models underutilize quantum states' potential due to oversimplified or incomplete mechanisms. To address this limitation, we introduce the Quantum Complex-Valued Self-Attention Model (QCSAM), the first framework to leverage complex-valued similarities, which captures amplitude and phase relationships between quantum states more comprehensively. To achieve this, QCSAM extends the Linear Combination of Unitaries (LCUs) into the Complex LCUs (CLCUs) framework, enabling precise complex-valued weighting of quantum states and supporting quantum multi-head attention. Experiments on MNIST and Fashion-MNIST show that QCSAM outperforms recent quantum self-attention models, including QKSAN, QSAN, and GQHAN. With only 4 qubits, QCSAM achieves 100% and 99.2% test accuracies on MNIST and Fashion-MNIST, respectively. Furthermore, we evaluate scalability across 3-8 qubits and 2-4 class tasks, while ablation studies validate the advantages of complex-valued attention weights over real-valued alternatives. This work advances quantum machine learning by enhancing the expressiveness and precision of quantum self-attention in a way that aligns with the inherent complexity of quantum mechanics.

📄 PDF Abstract BibTeX arXiv:2503.19002

Code (0)

등록된 구현이 없습니다.

Tasks

modelMulti-class Classification Quantum Machine Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Attention 설명 없음

CNM: An Interpretable Complex-valued Network for Matching

2019-04-10 · NAACL 2019 6 · Qiuchi Li, Benyou Wang, Massimo Melucci

This paper seeks to model human language by the mathematical framework of quantum physics. With the well-designed mathematical formulations in quantum physics, this framework unifies different linguistic units in a singl…

Benchmarking Question Answering

Complex-Valued Time-Frequency Self-Attention for Speech Dereverberation

2022-11-22 · Vinay Kothapally, John H. L. Hansen

Several speech processing systems have demonstrated considerable performance improvements when deep complex neural networks (DCNN) are coupled with self-attention (SA) networks. However, the majority of DCNN-based studie…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Speech Dereverberation speech-recognition+1

Learning Complex Word Embeddings in Classical and Quantum Spaces

2024-12-18 · Carys Harvey, Stephen Clark, Douglas Brown, Konstantinos Meichanetzidis

We present a variety of methods for training complex-valued word embeddings, based on the classical Skip-gram model, with a straightforward adaptation simply replacing the real-valued vectors with arbitrary vectors of co…

C++ code Word Embeddings

Paraconsistent Foundations for Quantum Probability

2021-01-19 · Ben Goertzel

It is argued that a fuzzy version of 4-truth-valued paraconsistent logic (with truth values corresponding to True, False, Both and Neither) can be approximately isomorphically mapped into the complex-number algebra of qu…

Integrating Quantum-Classical Attention in Patch Transformers for Enhanced Time Series Forecasting

2025-03-31 · Sanjay Chakraborty, Fredrik Heintz

QCAAPatchTF is a quantum attention network integrated with an advanced patch-based transformer, designed for multivariate time series forecasting, classification, and anomaly detection. Leveraging quantum superpositions,…

Anomaly Detection Multivariate Time Series Forecasting Time Series Time Series Forecasting