Quantum theory provides non-classical principles, such as superposition and entanglement, that inspires promising paradigms in machine learning. However, most existing quantum-inspired fusion models rely solely on unitary or unitary-like transformations to generate quantum entanglement. While theoretically expressive, such approaches often suffer from training instability and limited generalizability. In this work, we propose a Quantum-inspired Neural Network with Quantum Jump (QiNN-QJ) for multimodal entanglement modelling. Each modality is firstly encoded as a quantum pure state, after which a differentiable module simulating the QJ operator transforms the separable product state into the entangled representation. By jointly learning Hamiltonian and Lindblad operators, QiNN-QJ generates controllable cross-modal entanglement among modalities with dissipative dynamics, where structured stochasticity and steady-state attractor properties serve to stabilize training and constrain entanglement shaping. The resulting entangled states are projected onto trainable measurement vectors to produce predictions. In addition to achieving superior performance over the state-of-the-art models on benchmark datasets, including CMU-MOSI, CMU-MOSEI, and CH-SIMS, QiNN-QJ facilitates enhanced post-hoc interpretability through von-Neumann entanglement entropy. This work establishes a principled framework for entangled multimodal fusion and paves the way for quantum-inspired approaches in modelling complex cross-modal correlations.
Quantum theory provides non-classical principles, such as superposition and entanglement, that inspires promising paradigms in machine learning. However, most existing quantum-inspired fusion models rely solely on unitary or unitary-like transformations to generate quantum entanglement. While theoretically expressive, such approaches often suffer from training instability and limited generalizability. In this work, we propose a Quantum-inspired Neural Network with Quantum Jump (QiNN-QJ) for multimodal entanglement modelling. Each modality is firstly encoded as a quantum pure state, after which a differentiable module simulating the QJ operator transforms the separable product state into the entangled representation. By jointly learning Hamiltonian and Lindblad operators, QiNN-QJ generates controllable cross-modal entanglement among modalities with dissipative dynamics, where structured stochasticity and steady-state attractor properties serve to stabilize training and constrain entanglement shaping. The resulting entangled states are projected onto trainable measurement vectors to produce predictions. In addition to achieving superior performance over the state-of-the-art models on benchmark datasets, including CMU-MOSI, CMU-MOSEI, and CH-SIMS, QiNN-QJ facilitates enhanced post-hoc interpretability through von-Neumann entanglement entropy. This work establishes a principled framework for entangled multimodal fusion and paves the way for quantum-inspired approaches in modelling complex cross-modal correlations.
Video data is multimodal in its nature, where an utterance can involve linguistic, visual and acoustic information. Therefore, a key challenge for video sentiment analysis is how to combine different modalities for sentiment recognition effectively. The latest neural network approaches achieve state-of-the-art performance, but they neglect to a large degree of how humans understand and reason about sentiment states. By contrast, recent advances in quantum probabilistic neural models have achieved comparable performance to the state-of-the-art, yet with better transparency and increased level of interpretability. However, the existing quantum-inspired models treat quantum states as either a classical mixture or as a separable tensor product across modalities, without triggering their interactions in a way that they are correlated or non-separable (i.e., entangled). This means that the current models have not fully exploited the expressive power of quantum probabilities. To fill this gap, we propose a transparent quantum probabilistic neural model. The model induces different modalities to interact in such a way that they may not be separable, encoding crossmodal information in the form of non-classical correlations. Comprehensive evaluation on two benchmarking datasets for video sentiment analysis shows that the model achieves significant performance improvement. We also show that the degree of non-separability between modalities optimizes the post-hoc interpretability.
Sentiment, emotion, and sarcasm analysis in multimodal dialogues is crucial for understanding the underlying intentions and attitudes expressed by individuals. Traditional methods often struggle to capture the full intensity of these polarities, leading to less accurate results. To address this limitation, we propose a quantum-inspired approach leveraging Quantum Neural Networks (QNNs) for enhanced classification and intensity analysis. A key component of our method is the Variational Quantum Eigensolver (VQE), a hybrid quantum-classical algorithm that optimizes the parameters of the QNN by minimizing the eigenvalues of a Hamiltonian system. This optimization enables the network to learn complex relationships in multimodal data more effectively. Our approach surpasses state-of-the-art methods, achieving up to 7.5 % higher accuracy and 6.8 % greater precision. Experiments on benchmark datasets such as MUStARD, Memotion, CMU-MOSEI, and MELD demonstrate its effectiveness, with an F1-score of 87.3 % on CMU-MOSEI. This method is particularly beneficial in domains like social media, customer support, and entertainment, where both verbal and non-verbal cues play a critical role in accurate sentiment analysis .
A long-standing goal in the field of Artificial Intelligence (AI) is to develop systems that can perceive and understand human multimodal language. This requires both the consideration of context in the form of surrounding utterances in a conversation, i.e., context modelling, as well as the impact of different modalities (e.g., linguistic, visual acoustic), i.e., multimodal fusion. In the last few years, significant strides have been made towards the interpretation of human language due to simultaneous advancement in deep learning, data gathering and computing infrastructure. AI models have been investigated to either model interactions across distinct modalities, i.e., linguistic, visual and acoustic, or model interactions across parties in a conversation, achieving unprecedented levels of performance. However, AI models are often designed with only performance as their design target, leaving aside other essential factors such as transparency, interpretability, and how humans understand and reason about cognitive states. In line with this observation, in this dissertation, we develop quantum probabilistic neural models and techniques that allow us to capture rational and irrational cognitive biases, without requiring a priori understanding and identification of them. First, we present a comprehensive empirical comparison of state-of-the-art (SOTA) modality fusion strategies for video sentiment analysis. The findings provide us helpful insights into the development of more effective modality fusion models incorporating quantum-inspired components. Second, we introduce an end-to-end complex-valued neural model for video sentiment analysis, simulating quantum procedural steps, outside of physics, into the neural network modelling paradigm. Third, we investigate non-classical correlations across different modalities. In particular, we describe a methodology to model interactions between image and text for an information retrieval scenario. The results provide us with theoretical and empirical insights to develop a transparent end-to-end probabilistic neural model for video emotion detection in conversations, capturing non-classical correlations across distinct modalities. Fourth, we introduce a theoretical framework to model user's cognitive states underlying their multimodal decision perspectives, and propose a methodology to capture interference of modalities in decision making. Overall, we show that our models advance the SOTA on various affective analysis tasks, achieve high transparency due to the mapping to quantum physics meanings, and improve post-hoc interpretability, unearthing useful and explainable knowledge about cross-modal interactions.
This article proposes a quantum multimodal neural network (QMNN) model that can be implemented on parameterized quantum circuits (PQCs), providing a novel avenue for processing multimodal data and performing advanced multimodal sentiment analysis tasks. The comprehensive QMNN model is structured into four fundamental blocks: multimodal data preprocessing, unimodal feature extraction, multimodal feature fusion, and optimization. Through these blocks, multimodal data are initially preprocessed and encoded into quantum states. Subsequently, visual and textual features are extracted from the quantum states and are then integrated to learn the interactions between different modalities. Finally, the model parameters are fine-tuned to optimize the sentiment analysis performance. Simulation results confirm that QMNN surpasses state-of-the-art baselines, using significantly lower input dimensions and substantially fewer parameters than classical models. Furthermore, the entanglement, integrity, robustness, and scalability of the model are analyzed in depth. Internally, the strong entanglement within the multimodal fusion block enhances interactions between textual and visual features, and the integrity of the model reflects the indispensable contribution of each component to the overall performance. Externally, robustness ensures the model operates stably under noisy conditions and incomplete inputs, and scalability enables it to efficiently adapt to varying architectural depths and widths. The above simulation results and performance analyses showcase the comprehensive strength of our proposed model.
Multimodal vision-language systems typically fuse image and text embeddings through classical operators such as concatenation, attention, bilinear pooling, or tensor interactions. We propose Quantum Entangled Multimodal Fusion Networks (QEMFN), a hybrid quantum-classical framework that introduces parameterized entanglement as a structured inductive bias for multimodal fusion. Pretrained visual and textual features are projected into compact latent spaces, encoded as angle-parameterized quantum states, processed through intra-modal and paired cross-modal entangling circuits, and measured to produce fused representations for retrieval. Under matched parameter budgets and identical frozen CLIP backbones, QEMFN outperforms classical fusion baselines on COCO-5k and Flickr30k, including multilayer perceptron, tensor fusion, FiLM, cross-attention, compact transformer, and a dequantized paired-topology analogue. An ablation suite isolates the quantum module's contribution from the surrounding classical projections, and quantum-centric analyses report Meyer-Wallach entangling capability, expressibility, gradient variance against barren-plateau bounds, and entropy-performance correlation under controls for training progress alongside an intervention study on the entangling component. QEMFN is executed under shot-based estimation, a noise-modeled fake backend, and a real superconducting device with zero-noise extrapolation. This work does not claim quantum computational advantage; the contribution is the framework together with a controlled empirical and quantum-centric evaluation that positions trainable entanglement as an interpretable, hardware-executable fusion mechanism at scales accessible on contemporary devices.
Quantum-inspired neural networks (QINNs) have emerged as a promising approach to leveraging quantum computational principles for accelerating and enhancing artificial intelligence. However, a significant limitation of existing QINNs lies in their failure to fully capture the essence of quantum entanglement, a cornerstone of quantum mechanics. This paper proposes a novel architecture, termed Entangled Node Representation (ENR) QINNs, which directly incorporates true quantum entanglement into the network structure. The core idea is to represent nodes as entangled qubits, allowing for inherent correlations between nodes that surpass the limitations of classical neural networks. We postulate that this approach will dramatically improve learning efficiency by enabling the network to explore a wider solution space and converge faster. The proposed ENR QINNs introduce a formal mathematical framework for modeling and training these networks, exploring the potential of superposition and interference effects within the network's architecture. The theoretical analysis demonstrates that the ENR QINNs possess the potential to achieve exponential speedups in computation compared to traditional neural networks, particularly in tasks involving complex correlations. We outline key considerations for the design and training of ENR QINNs, including qubit representation choices, entanglement management strategies, and optimization algorithms specifically tailored to exploit the quantum properties of the network. Further research will focus on experimental validation and scaling the architecture for real-world applications.