Expressive and Scalable Quantum Fusion for Multimodal Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Nguyen, Tuyen, Hoang, Trong Nghia, Nguyen, Phi Le, Vu, Hai L., Thang, Truong Cong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914081353498624
author Nguyen, Tuyen
Hoang, Trong Nghia
Nguyen, Phi Le
Vu, Hai L.
Thang, Truong Cong
author_facet Nguyen, Tuyen
Hoang, Trong Nghia
Nguyen, Phi Le
Vu, Hai L.
Thang, Truong Cong
contents The aim of this paper is to introduce a quantum fusion mechanism for multimodal learning and to establish its theoretical and empirical potential. The proposed method, called the Quantum Fusion Layer (QFL), replaces classical fusion schemes with a hybrid quantum-classical procedure that uses parameterized quantum circuits to learn entangled feature interactions without requiring exponential parameter growth. Supported by quantum signal processing principles, the quantum component efficiently represents high-order polynomial interactions across modalities with linear parameter scaling, and we provide a separation example between QFL and low-rank tensor-based methods that highlights potential quantum query advantages. In simulation, QFL consistently outperforms strong classical baselines on small but diverse multimodal tasks, with particularly marked improvements in high-modality regimes. These results suggest that QFL offers a fundamentally new and scalable approach to multimodal fusion that merits deeper exploration on larger systems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06938
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Expressive and Scalable Quantum Fusion for Multimodal Learning
Nguyen, Tuyen
Hoang, Trong Nghia
Nguyen, Phi Le
Vu, Hai L.
Thang, Truong Cong
Quantum Physics
Artificial Intelligence
The aim of this paper is to introduce a quantum fusion mechanism for multimodal learning and to establish its theoretical and empirical potential. The proposed method, called the Quantum Fusion Layer (QFL), replaces classical fusion schemes with a hybrid quantum-classical procedure that uses parameterized quantum circuits to learn entangled feature interactions without requiring exponential parameter growth. Supported by quantum signal processing principles, the quantum component efficiently represents high-order polynomial interactions across modalities with linear parameter scaling, and we provide a separation example between QFL and low-rank tensor-based methods that highlights potential quantum query advantages. In simulation, QFL consistently outperforms strong classical baselines on small but diverse multimodal tasks, with particularly marked improvements in high-modality regimes. These results suggest that QFL offers a fundamentally new and scalable approach to multimodal fusion that merits deeper exploration on larger systems.
title Expressive and Scalable Quantum Fusion for Multimodal Learning
topic Quantum Physics
Artificial Intelligence
url https://arxiv.org/abs/2510.06938