Weighted meta-graph based mobile application recommendation through matrix factorisation and neural networks

Numerous mobile applications (apps) with different functions meet the various needs of users, but users have to spend a lot of time selecting suitable mobile apps. How to select relevant mobile apps for users has become an important issue. Existing studies mainly utilise context, user interest, privacy, security, version, and heterogeneous information to make mobile app recommendations. However, they have at least one of the following limitations: (1) Don't fully integrate the rich heterogeneous information; (2) Don't capture complex structural and semantic information; (3) Don't differentiate the importance of different semantic meta-graphs; (4) Don't consider the influence of different users' rating criteria. Therefore, the predictive performance of these methods is relatively limited. This paper considers the influence of different users' rating criteria for the same app and proposes a weighted meta-graph based mobile app recommendation approach by leveraging matrix factorisation and neural networks. Specifically, the similarity measurement between users and apps considers the difference in users' rating criteria under various semantic meta-graph patterns. The matrix factorisation technology is used to acquire the user's and the app's latent feature matrices. The importance of various semantic meta-graphs is distinguished by exploiting the weight learning. The neural network technology is employed to learn interactions between users and apps, thereby predicting the user's preference for unobserved apps. Experimental results demonstrate the superiority of the proposed approach, the effectiveness of considering differences in users' rating criteria, and the importance of differentiating various semantic meta-graphs.