Collaborative filtering recommendation algorithm based on graph convolution attention mechanism

Abstract

The invention discloses a collaborative filtering recommendation algorithm based on a graph convolution attention mechanism. The method comprises the steps of firstly collecting and processing data and dividing a data set, secondly constructing a GACF model, and finally training the model and recommending by predicting an association score between a user and an item. According to the graph convolution attention mechanism collaborative filtering model provided by the invention, firstly, user-project interaction information is mapped to a vector space by using a graph embedding technology, then, the embedding expression of a user-project interaction graph is learned through a graph convolution network, and then, different weights are allocated to neighbor nodes by using an attention mechanism. By aggregating the feature information of the neighbor nodes, the weight between the neighbor nodes can only depend on the feature expression between the nodes, so that the generalization ability of the model is improved, and finally, a plurality of embedded vectors learned by a graph convolution layer are weighted and aggregated to obtain the association score between the user and the project.

Description

Technical field [0001] The present invention belongs to the technical field of computer artificial intelligence, and in particular, the present invention relates to a synergistic filtration recommendation algorithm based on the graphic volume attention mechanism. Background technique [0002] In this era of this data large explosion, in order to relieve information overload issues, the recommended system has been widely used in personalized information filtration. The most widely recommended technique for application is a collaborative filtering recommendation algorithm. It is based on similar users to exhibit similar preferences, and explore users's hidden preferences through user history behavior, and perform implicit preferences according to user implicit preferences recommend. Early recommended models directly use the ID number of users and projects as embedded vectors, resulting in limitations of embedded expression. Subsequently, many researchers increase user IDs and its i...

AI Technical Summary

Problems solved by technology

However, the way they aggregate the features of neighbor nodes depends entirely on the graph structure, which is not conducive to extending to other graph structures, thus limiting the generalization ability of the model

Images