FG-CF: Friends-aware graph collaborative filtering for POI recommendation

Collaborative filtering approach greatly promotes the development and application of personalized recommendation. In location-based social networks (LBSNs), the sparsity of check-in data is one of the main obstacles for traditional Point-of-Interest (POI) recommendation models. Graph convolutional network (GCN) is an efficient tool to overcome this kind of problems, which enhances the representational ability of embeddings by capture high-order connectivity of users and POIs. In real applications, social tie is a crucial factor for POI recommendation that ignored in most current graph-based methods. Moreover, most message aggregation functions fail to capture contextual information. To address these problems, a novel framework named Friends-aware Graph Collaborative Filtering (FG-CF) is proposed in this paper, which incorporates social information into a user-POI graph. Firstly, a user-POI correlation matrix is estimated by check-in data and social links, and then, user embedding is updated according to the user-POI correlation matrix. Secondly, interaction messages are constructed in a novel way by integrating nodes' ego embeddings, neighbors' embeddings and social embeddings. Thirdly, by aggregating previous state embeddings and non-linear combination of neighbor messages with interaction messages, a new message aggregation function is present to update user and POI embeddings. Fourthly, we concatenate embeddings from each additional interaction layer to get the final embeddings, and inner product is used to compute the preference score of a user to a targeted POI. Finally, extensive experiments on two largescale LBSN datasets demonstrate the superiority of our model over several state-of-the-art approaches.(c) 2022 Elsevier B.V. All rights reserved.

Automated summary

This paper proposes a novel framework called Friends-aware Graph Collaborative Filtering (FG-CF), which incorporates social information into the user-POI graph. By considering social ties and contextual information, the framework improves the accuracy and effectiveness of personalized recommendation.