QAHAN: A Quantum Annealing Hard Attention Network

TL;DR

This paper introduces QAHAN, a quantum annealing-based hard attention network that improves convergence speed, accuracy stability, and noise robustness in image classification tasks by leveraging quantum tunneling effects.

Contribution

It presents a novel quantum annealing hard attention mechanism and network architecture that outperform traditional methods in convergence speed and robustness.

Findings

Faster convergence to global optimum.

Smoother accuracy and loss curves.

Enhanced noise robustness.

Abstract

Hard Attention Mechanisms (HAMs) effectively filter essential information discretely and significantly boost the performance of machine learning models on large datasets. Nevertheless, they confront the challenge of non-differentiability, which raises the risk of convergence to a local optimum. Quantum Annealing (QA) is expected to solve the above dilemma. We propose a Quantum Annealing Hard Attention Mechanism (QAHAM) for faster convergence to the global optimum without the need to compute gradients by exploiting the quantum tunneling effect. Based on the above theory, we construct a Quantum Annealing Hard Attention Network (QAHAN) on D-Wave and Pytorch platforms for MNIST and CIFAR-10 multi-classification. Experimental results indicate that the QAHAN converges faster, exhibits smoother accuracy and loss curves, and demonstrates superior noise robustness compared to two traditional HAMs. Predictably, our scheme accelerates the convergence between the fields of quantum algorithms and machine learning, while advancing the field of quantum machine vision.