EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid Quantum–Classical Graph Transformers for Efficient Sentiment Analysis

Shamminuj Aktar, Andreas Bärtschi, Abdel‐Hameed A. Badawy, Stephan Eidenbenz

Advanced Quantum Technologies · 2026-03 · 9 (3)

DOI: 10.1002/qute.202501004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Quantum Technologies, online erschienen am 27.03.2026. Verfasst von Shamminuj Aktar und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Laboratory Directed Research and Development, Los Alamos National Laboratory.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Quantum Machine Learning (QML) offers a promising paradigm that leverages quantum computing principles to develop efficient and expressive models for learning from complex and structured data. Recent advances in natural language processing (NLP) and artificial intelligence (AI) have demonstrated capabilities in understanding, generating, and reasoning over linguistic and multimodal information. In this work, we present the Quantum Graph Transformer (QGT) , a hybrid quantum–classical architecture that extends graph transformer capabilities through quantum self‐attention. The QGT models variable‐length sentences as token graphs, where both the embedding encoding and the self‐attention mechanisms are implemented using parameterized quantum circuits (PQCs), enabling efficient contextual learning with significantly fewer trainable parameters. We train QGT using both fully connected and ‐nearest‐neighbor graph structures and evaluate it on five benchmark sentiment‐classification datasets. Experimental results show that QGT consistently achieves higher or comparable accuracy to existing quantum NLP models and outperforms a Classical Graph Transformer (CGT) baseline with identical architecture, achieving fewer parameters while requiring 3– fewer samples to reach comparable performance. These findings highlight the potential of graph‐based quantum models as scalable and data‐efficient architectures for natural language understanding.

Förderung

  • Laboratory Directed Research and Development
  • Los Alamos National Laboratory

Zitieren

APA

Aktar, S., Bärtschi, A., Badawy, A. A., & Eidenbenz, S. (2026). Hybrid Quantum–Classical Graph Transformers for Efficient Sentiment Analysis. Advanced Quantum Technologies, 9(3). https://doi.org/10.1002/qute.202501004

Vancouver

Aktar S, Bärtschi A, Badawy AA, Eidenbenz S. Hybrid Quantum–Classical Graph Transformers for Efficient Sentiment Analysis. Advanced Quantum Technologies. 2026;9(3). doi:10.1002/qute.202501004

BibTeX
@article{Aktar2026,
  author = {Aktar, Shamminuj and Bärtschi, Andreas and Badawy, Abdel‐Hameed A. and Eidenbenz, Stephan},
  title = {Hybrid Quantum–Classical Graph Transformers for Efficient Sentiment Analysis},
  journal = {Advanced Quantum Technologies},
  year = {2026},
  volume = {9},
  number = {3},
  doi = {10.1002/qute.202501004}
}
Kostenlos starten →