Multi-perspective social recommendation method with graph representation learning

Article Computer Science, Artificial Intelligence

A graph embedding based model for fine-grained POI recommendation

Xiaojiao Hu et al.

Summary: This study proposes a novel POI-based item recommendation model via graph embedding, which effectively addresses data sparsity and cold start issues, as well as accurately capturing dynamic user preferences. Experimental results demonstrate that the model significantly outperforms existing baselines on three datasets.

NEUROCOMPUTING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Leveraging neighborhood session information with dual attentive neural network for session-based recommendation

Yuan Wu et al.

Summary: In this study, a novel session-based recommendation method LNIDA is proposed to improve recommendation effectiveness by utilizing neighborhood session information and a dual attentive neural network. Experimental results on three benchmark datasets show the effectiveness of LNIDA in modeling both current session information and neighborhood session information simultaneously.

NEUROCOMPUTING (2021)

添加到收藏夹

Review Computer Science, Artificial Intelligence

CARM: Confidence-aware recommender model via review representation learning and historical rating behavior in the online platforms

Duantengchuan Li et al.

Summary: This article proposes a confidence-aware recommender model via review representation learning and historical rating behavior, constructing the interaction latent factor of user and item by exploiting review information interactivity to enhance model accuracy.

NEUROCOMPUTING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Enhancing social recommendation via two-level graph attentional networks

Yanbin Jiang et al.

Summary: The study proposes to integrate social influence into embeddings by utilizing neighborhood propagation on two coupled graphs, and develops a new social recommendation framework with hierarchical attention to adaptively acquire relative importance for different factors. Experimental results demonstrate the superior performance of this approach and the effectiveness of simultaneous neighborhood propagation on two graphs.

NEUROCOMPUTING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence