Abstract
In recent years, graph neural networks (GNNS) have been demonstrated to be a powerful way to learn graph data. The existing recommender systems based on the implicit factor models mainly use the interactive information between users and items for training and learning. A user–item graph, a user–attribute graph, and an item–attribute graph are constructed according to the interactions between users and items. The latent factors of users and items can be learned in these graph structure data. There are many methods for learning the latent factors of users and items. Still, they do not fully consider the influence of node attribute information on the representation of the latent factors of users and items. We propose a rating prediction recommendation model, short for LNNSR, utilizing the level of information granularity allocated on each attribute by developing a granular neural network. The different granularity distribution proportion weights of each attribute can be learned in the granular neural network. The learned granularity allocation proportion weights are integrated into the latent factor representation of users and items. Thus, we can capture user-embedding representations and item-embedding representations more accurately, and it can also provide a reasonable explanation for the recommendation results. Finally, we concatenate the user latent factor-embedding and the item latent factor-embedding and then feed it into a multi-layer perceptron for rating prediction. Extensive experiments on two real-world datasets demonstrate the effectiveness of the proposed framework.
Highlights
With the rapid development of the Internet, especially the mobile Internet, the amount of information on the Internet is growing explosively
In order to demonstrate the effectiveness of the proposed framework, LNNSR, we make an experimental comparison with the representative baseline model on the above two real data sets
DCF obtains much better performance than probabilistic matrix factorization (PMF), which is only based on matrix factorization, and shows the effectiveness of using deep learning to extract auxiliary information
Summary
With the rapid development of the Internet, especially the mobile Internet, the amount of information on the Internet is growing explosively. Obtaining meaningful content for users from a large amount of digital information has become a hot research task. A personalized recommendation can help users obtain useful information efficiently and accurately in massive information resources. Some recommender models utilize matrix factorization to learn the representations of users and items based on their historical interactions [1,2]. Matrix factorization-based recommender systems can only use matrix scores for modeling and recommending, while we cannot fully utilize some important feature information. DCF is an early hybrid recommendation algorithm combining probability matrix decomposition and a noise-reduction self-encoder [9]. In 2016, deep-learning technology began to be applied in the field of recommender systems. Referring to the idea of word2vec, the item2vec algorithm takes the user’s behavior sequence as a sentence for representation and learning [10]. Many classical models have been proposed in the same period, such as NFM, AFM, etc. [12,13]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
