Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Afane, Mohamed, Ebbrecht, Gabrielle, Wang, Ying, Chen, Juntao, Farooq, Junaid
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2503.21815
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915217468817408
author Afane, Mohamed
Ebbrecht, Gabrielle
Wang, Ying
Chen, Juntao
Farooq, Junaid
author_facet Afane, Mohamed
Ebbrecht, Gabrielle
Wang, Ying
Chen, Juntao
Farooq, Junaid
contents Quantum Neural Networks (QNNs) offer promising capabilities for complex data tasks, but are often constrained by limited qubit resources and high entanglement, which can hinder scalability and efficiency. In this paper, we introduce Adaptive Threshold Pruning (ATP), an encoding method that reduces entanglement and optimizes data complexity for efficient computations in QNNs. ATP dynamically prunes non-essential features in the data based on adaptive thresholds, effectively reducing quantum circuit requirements while preserving high performance. Extensive experiments across multiple datasets demonstrate that ATP reduces entanglement entropy and improves adversarial robustness when combined with adversarial training methods like FGSM. Our results highlight ATPs ability to balance computational efficiency and model resilience, achieving significant performance improvements with fewer resources, which will help make QNNs more feasible in practical, resource-constrained settings.
format Preprint
id arxiv_https___arxiv_org_abs_2503_21815
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ATP: Adaptive Threshold Pruning for Efficient Data Encoding in Quantum Neural Networks
Afane, Mohamed
Ebbrecht, Gabrielle
Wang, Ying
Chen, Juntao
Farooq, Junaid
Quantum Physics
Artificial Intelligence
Machine Learning
Quantum Neural Networks (QNNs) offer promising capabilities for complex data tasks, but are often constrained by limited qubit resources and high entanglement, which can hinder scalability and efficiency. In this paper, we introduce Adaptive Threshold Pruning (ATP), an encoding method that reduces entanglement and optimizes data complexity for efficient computations in QNNs. ATP dynamically prunes non-essential features in the data based on adaptive thresholds, effectively reducing quantum circuit requirements while preserving high performance. Extensive experiments across multiple datasets demonstrate that ATP reduces entanglement entropy and improves adversarial robustness when combined with adversarial training methods like FGSM. Our results highlight ATPs ability to balance computational efficiency and model resilience, achieving significant performance improvements with fewer resources, which will help make QNNs more feasible in practical, resource-constrained settings.
title ATP: Adaptive Threshold Pruning for Efficient Data Encoding in Quantum Neural Networks
topic Quantum Physics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2503.21815