In recommender systems research, the data sparsity problem has driven the development of hybrid recommendation algorithms integrating multimodal information and the application of graph neural networks (GNNs). However, conventional GNNs relying on homogeneous Euclidean embeddings fail to effectively model the non-Euclidean geometric manifold structures prevalent in real-world scenarios, consequently constraining the representation capacity for heterogeneous interaction patterns and compromising recommendation accuracy. As a consequence, the representation capability for heterogeneous interaction patterns is restricted, thereby affecting the overall representational power and recommendation accuracy of the models. In this paper, we propose a hyperbolic graph neural network model with contrastive learning for rating–review recommendation, implementing a dual-graph construction strategy. First, it constructs a review-aware graph to integrate rich semantic information from reviews, thus enhancing the recommendation system’s context awareness. Second, it builds a user–item interaction graph to capture user preferences and item characteristics. The hyperbolic graph neural network architecture enables joint learning of high-order features from these two graphs, effectively avoiding the embedding distortion problem commonly associated with high-order feature learning. Furthermore, through contrastive learning in hyperbolic space, the model effectively leverages review information and user–item interaction data to enhance recommendation system performance. Experimental results demonstrate that the proposed algorithm achieves excellent performance on multiple real-world datasets, significantly improving recommendation accuracy.
In this paper, the uniform asymptotic stability (UAS) of nonlinear time-varying delay differential inclusions is investigated. Some new stability criteria are established from the output-to-state perspective for time-varying delay differential inclusions. Furthermore, the limiting systems associated with the time-varying delay differential inclusions are introduced to verify the weakly-zero-state-detectability (WZSD) condition. The proposed criteria can be viewed as extensions of LaSalle’s invariance principle to time-varying delay systems with multiple solutions. Finally, a tracking control example is presented to demonstrate the effectiveness of the obtained results.
Multimodal Recommender Systems (MRSs) leverage heterogeneous data to alleviate data sparsity, yet they remain vulnerable to spurious correlations and modality noise that obscure the rationale behind recommendations. To address this, we propose the Multimodal Counterfactual Fusion with the Causality-Guided Contrastive Learning (MCFC) framework. MCFC integrates three core modules: a Multimodal Structural Causal Model that motivates the assumed causal paths of multimodal biases; a Counterfactual Feature Fusion module with causal effect-inspired weighting that estimates each modality’s contribution via score perturbations and suppresses noisy features; and a Causality-Guided Contrastive Learning mechanism that builds counterfactual in-batch negatives to enforce invariant and robust representations. Extensive experiments on four public Amazon datasets show that MCFC consistently outperforms state-of-the-art baselines on Recall@K and NDCG@K, improving Recall@20 by 29.9% over the strongest baseline on the highly sparse Baby dataset. Ablation studies confirm the contribution of each module, evidencing MCFC’s robustness to modality noise and strong adaptability in sparse interaction settings.