Expressive and Scalable Quantum Fusion for Multimodal Learning
This proposes a new paradigm for multimodal fusion that could address scalability issues in classical methods, though it is currently incremental as it is demonstrated only on small tasks.
The paper tackles multimodal learning by introducing a quantum fusion mechanism (QFL) that uses parameterized quantum circuits to learn entangled feature interactions with linear parameter scaling, and in simulation, it consistently outperforms classical baselines on small multimodal tasks with marked improvements in high-modality regimes.
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.