# GQHAN: A Grover-inspired Quantum Hard Attention Network

arXiv: https://arxiv.org/abs/2401.14089 · HTML: https://mlsanity.com/paper/2401.14089/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 42 references that are in the map.
- First posted on arXiv 25 Jan 2024.

## Builds on (most cited first, 16 of 16)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Challenges and Opportunities in Quantum Machine Learning](https://mlsanity.com/paper/2303.09491/) (2023)
- [Quantum Natural Gradient](https://mlsanity.com/paper/1909.02108/) (2019)
- [Learning When and Where to Zoom with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.00425/) (2020)
- [Quantum Self-Attention Neural Networks for Text Classification](https://mlsanity.com/paper/2205.05625/) (2022)
- [Saccader: Improving Accuracy of Hard Attention Models for Vision](https://mlsanity.com/paper/1908.07644/) (2019)
- [Processing Megapixel Images with Deep Attention-Sampling Models](https://mlsanity.com/paper/1905.03711/) (2019)
- [QSAN: A Near-term Achievable Quantum Self-Attention Network](https://mlsanity.com/paper/2207.07563/) (2022)
- [Learning Visual Question Answering by Bootstrapping Hard Attention](https://mlsanity.com/paper/1808.00300/) (2018)
- [QKSAN: A Quantum Kernel Self-Attention Network](https://mlsanity.com/paper/2308.13422/) (2023)
- [Hard-Attention for Scalable Image Classification](https://mlsanity.com/paper/2102.10212/) (2021)
- [Multi-agent Reinforcement Learning for Dynamic Resource Management in 6G in-X Subnetworks](https://mlsanity.com/paper/2205.05036/) (2022)
- [Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Model](https://mlsanity.com/paper/2202.02212/) (2022)
- [Fast Black-Box Quantum State Preparation](https://mlsanity.com/paper/2009.10709/) (2020)

## Built on by (most cited first, 5 of 5)

- [Quantum Adjoint Convolutional Layers for Effective Data Representation](https://mlsanity.com/paper/2404.17378/) (2024)
- [HQCC: A Hybrid Quantum-Classical Classifier with Adaptive Structure](https://mlsanity.com/paper/2504.02167/) (2025)
- [Quantum Complex-Valued Self-Attention Model](https://mlsanity.com/paper/2503.19002/) (2025)
- [Quantum Attention by Overlap Interference: Predicting Classical and Many-Body Quantum Sequences](https://mlsanity.com/paper/2602.06699/) (2026)
- [QTrans: A Quantum Transformer for Sentiment Classification](https://mlsanity.com/paper/2609.12011/) (2026)

## Abstract (arXiv)

Numerous current Quantum Machine Learning (QML) models exhibit an inadequacy in discerning the significance of quantum data, resulting in diminished efficacy when handling extensive quantum datasets. Hard Attention Mechanism (HAM), anticipated to efficiently tackle the above QML bottlenecks, encounters the substantial challenge of non-differentiability, consequently constraining its extensive applicability. In response to the dilemma of HAM and QML, a Grover-inspired Quantum Hard Attention Mechanism (GQHAM) consisting of a Flexible Oracle (FO) and an Adaptive Diffusion Operator (ADO) is proposed. Notably, the FO is designed to surmount the non-differentiable issue by executing the activation or masking of Discrete Primitives (DPs) with Flexible Control (FC) to weave various discrete destinies. Based on this, such discrete choice can be visualized with a specially defined Quantum Hard Attention Score (QHAS). Furthermore, a trainable ADO is devised to boost the generality and flexibility of GQHAM. At last, a Grover-inspired Quantum Hard Attention Network (GQHAN) based on QGHAM is constructed on PennyLane platform for Fashion MNIST binary classification. Experimental findings demonstrate that GQHAN adeptly surmounts the non-differentiability hurdle, surpassing the efficacy of extant quantum soft self-attention mechanisms in accuracies and learning ability. In noise experiments, GQHAN is robuster to bit-flip noise in accuracy and amplitude damping noise in learning performance. Predictably, the proposal of GQHAN enriches the Quantum Attention Mechanism (QAM), lays the foundation for future quantum computers to process large-scale data, and promotes the development of quantum computer vision.