Social recommendation method and system based on graph convolutional network

Abstract

The invention discloses a social recommendation method and system based on a graph convolutional network, and belongs to the field of machine learning and social recommendation. The method mainly comprises the steps of data set construction, neighborhood aggregation, entity representation generation, model training and prediction and the like. According to the invention, two types of information of articles and social friends interacting with a user side are considered at the user side, and two types of information of users and collaborative similar articles interacting with an article side are considered at the article side, so that a user-article interaction network, a user social network and an article collaborative similar network are modeled in a unified network; and the embedding is improved by explicitly modeling the high-order connectivity among the user-article, the user social network and the article collaborative similar network, so that the deep potential interest preference of the user on the article can be captured, the semantic-rich user / article representation is finally generated, and the purpose of improving the recommendation accuracy is achieved.

Description

technical field [0001] The invention belongs to the field of machine learning and social recommendation, and in particular relates to a method and system for social recommendation based on graph convolution network. Background technique [0002] With the advancement of network technology, people can easily access a large amount of online information, such as commodities and movies. But at the same time, the problem of "information overload" is getting worse, causing users to spend a lot of time to get the information they want. Therefore, the recommendation system came into being, which aims to filter out a large amount of irrelevant information by analyzing the user's interests and needs and judging the relevant commodity sets. One of the most popular recommendation techniques currently is Collaborative Filtering (CF), which leverages users' historical interactions and makes recommendations based on their common preferences. In general, a learnable CF model has two key co...

AI Technical Summary

Problems solved by technology

However, when using GNN to model the connectivity information in the embedded function, there is often a lack of explicit encoding of the social relationship between users and the joint similarity relationship between items and items. These synergistic signals are in the user-item interaction is latent, which reveals behavioral similarities between users

More specifically, most existing methods only use descriptive features (such as IDs and attributes) to construct embedding functions, and the information utilization of social networks and item collaborative similarity networks often obtains corresponding embedding representations through different channels. Finally, the semantic information is fused by concatenation, etc., without considering the joint encoding of the relationship between the user-item interaction network, user social network, and item collaborative similarity network into the embedding learning process.

Images