Personalized knowledge-aware recommendation with collaborative and attentive graph convolutional networks

•A new framework (COAT) is proposed for personalized knowledge-aware recommendation.•Collaborative and attentive GNNs are designed to jointly model the UI and KG graphs.•Novel attention mechanisms are designed to achieve personalization.•An efficient graph convolutional layer is employed to tackle t...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition 2022-08, Vol.128, p.108628, Article 108628
Main Authors: Dai, Quanyu, Wu, Xiao-Ming, Fan, Lu, Li, Qimai, Liu, Han, Zhang, Xiaotong, Wang, Dan, Lin, Guli, Yang, Keping
Format: Article
Language:English
Subjects:
Attention mechanism
Graph convolutional network
Knowledge graph
Recommender system
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•A new framework (COAT) is proposed for personalized knowledge-aware recommendation.•Collaborative and attentive GNNs are designed to jointly model the UI and KG graphs.•Novel attention mechanisms are designed to achieve personalization.•An efficient graph convolutional layer is employed to tackle the sparsity issue.•COAT outperforms 10 state-of-the-art recommendation methods on benchmark datasets. Knowledge graphs (KGs) are increasingly used to solve the data sparsity and cold start problems of collaborative filtering. Recently, graph neural networks (GNNs) have been applied to build KG-based recommender systems and achieved competitive performance. However, existing GNN-based methods are either limited in their ability to capture fine-grained semantics in a KG, or insufficient in effectively modeling user-item interactions. To address these issues, we propose a novel framework with collaborative and attentive graph convolutional networks for personalized knowledge-aware recommendation. Particularly, we model the user-item graph and the KG separately and simultaneously with an efficient graph convolutional network and a personalized knowledge graph attention network, where the former aims to extract informative collaborative signals, while the latter is designed to capture fine-grained semantics. Collectively, they are able to learn meaningful node representations for predicting user-item interactions. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed method compared with state-of-the-arts.
ISSN:0031-3203
1873-5142
DOI:10.1016/j.patcog.2022.108628