This manuscript introduces a novel attention-based recommender system that leverages heterogeneous information networks (HINs) to extract user and item representations and utilizes a matrix factorization framework to model interactions between users and items with the aim of predicting the ratings of users on items.
A novel BADLGRS model is evaluated across four datasets and demonstrates superior performance when compared to existing methods, and consistently outperform existing models in group recommendation tasks.
Gopisetty Rathnamma, Kommanaboyina Sai Vijaya Lakshmi, Vadige Sathish Kumar et al.· Cognitive Computation· 0 citations
A two-stage recommendation architecture that integrates topic attention mechanisms and user interaction relationships is proposed that can maintain stable recommendation performance under different levels of interaction sparsity.
Jun-Ya Zhang, Shuang-Feng Wu· International Journal on Mob...· 0 citations
A novel neural network called the Co-occurrence Graph Neural Network (CoGNN), which utilizes two co-occurrence graphs to establish user and item relationships and outperforms various baseline models in terms of recommendation accuracy and algorithm convergence.
Chao Lin, Y. Lin, You-Yu Wang et al.· Multimedia Systems· 0 citations
A social relationship adjustment loss function, which dynamically adjusts the weights of social connections, and the Hilbert-Schmidt independence criterion loss function, which reduces the dependence between pre- and post-adjusted user/item embeddings, thereby amplifying the effect of adjusted social relationships on t...
