Exploiting multi-attention network with contextual influence for point-of-interest recommendation
- PDF / 1,960,813 Bytes
- 14 Pages / 595.224 x 790.955 pts Page_size
- 64 Downloads / 183 Views
Exploiting multi-attention network with contextual influence for point-of-interest recommendation Liang Chang1,2 · Wei Chen3
· Jianbo Huang1 · Chenzhong Bin1 · Wenkai Wang1
Accepted: 6 August 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Point-of-Interest (POI) recommendation has become an important service on Location-Based Social Networks (LBSNs). In order to improve the performance of recommendation, besides the check-in data generated in LBSNs, researchers are striving to exploit various auxiliary information such as social relation among users and geographical influence among neighbourhood POIs. However, existing works cannot effectively study the diverse degrees of influence from user’s friends, neither are they able to capture the feature impacts of POIs in the preference modelling process. To overcome these challenges, by making use of a Multi-Attention Network to learn the Contextual influence of both users and POIs, this paper presents a model named MANC for POI recommendation. The MANC model consists of two parts: a user-friend module and a POI neighbourhood module. Unlike existing works which treat the influences from different friends of a user equally, the user-friend module in MANC applies an attention-based memory component to generate specific relation vectors which can differentiate the influence from the aspect of interest, and applies a friend-level attention network to adaptively capture the preferences of users. For the POI contextual information, the POI neighbourhood module in MANC applies a featurelevel attention network to capture the latent features of neighbourhood POIs, and applies a POI-level attention network to capture the geographical influence among POIs. Extensive experiments are carried out, and it is shown that the MANC model achieves better performance than other state-of-the-art methods. Keywords Point-of-interest · Recommendation system · Attention network · Collaborative filtering · Contextual information
1 Introduction Advancements of mobile internet technologies have led to the emergence of location-based social networks (LBSNs) services such as Foursquare, Yelp, and Facebook [22, 25, 27]. More and more individuals are sharing their experience of visiting places with their friends via LBSNs. The large amount of check-in data generated in LBSNs can be used for the recommendation of places such as cafes and museums which are called Point-of-Interests (POIs). POI recommendation plays an important role in helping visitors to find interesting places. However, different from traditional e-commerce recommendation, POI recommendation often suffers the problem of sparse
Wei Chen
w [email protected]
Extended author information available on the last page of the article.
data. Furthermore, the check-in data of users for POI recommendation is implicit data rather than explicit ratings (e.g., 1-5). As a result, traditional collaborative filtering (CF) methods such as matrix factorization (MF) [16] and its various extensions [11, 19, 20] are un
