Context-aware graph convolution recommendation system

Abstract

The invention discloses a context-aware graph convolution recommendation system. The context-aware graph convolution recommendation system comprises an encoder, a graph convolution layer and a decoder, the encoder associates each non-zero feature of the input user information, article information and context information with a hidden space vector, and combines the hidden space vectors from three domains of the user information, the article information and the context information; in the graph convolution layer, graph convolution operation is performed based on a pre-constructed user article bipartite graph with attributes in combination with output of an encoder, and final feature representation of a user and an article is obtained through multiple times of graph convolution operation; andthe decoder predicts the preference degree of the user to the article under the context information based on the final feature representation of the user and the article and the associated embeddingset of the context information. The system is a universal recommendation system framework suitable for online service, various auxiliary information can be combined, the collaborative filtering effectcan be captured, and the model performance is improved.

Description

technical field [0001] The invention relates to the fields of recommendation systems and graph data mining, in particular to a context-aware graph convolution recommendation system. Background technique [0002] As an important tool to alleviate information overload and improve user experience, personalized recommendation system has become an indispensable service in the current Internet. The collaborative filtering model is one of the most representative recommendation models. It uses the historical interaction records of users and items, such as clicks, purchases, etc., to map each user and item to a high-dimensional vector space, and calculates the similarity between vectors. for personalized recommendations. Recently, due to the great success of graph neural network (GNN) in the fields of image processing and natural language processing, more and more researchers have introduced GNN into the recommendation system and modeled the collaborative filtering signal as a user-...

AI Technical Summary

Problems solved by technology

Comprehensive analysis of recent CARS progress, we found that they have the following deficiencies: 1) They use standard supervised learning strategies, ignoring the linkage between data samples, which will cause the learned model to fail to capture the collaborative filtering effect well, Because identifying collaborative filtering effects needs to consider multiple interaction records at the same time; 2) they often have high complexity because they use well-designed network structures in order to model complex feature interactions, and when serving online, it is necessary to Each user-candidate item pair is forwarded through the network once. This inefficient and time-consuming inference strategy is not suitable for online services.

Images