An Information Recommendation Method Based on Graph Convolution and Neural Collaborative Filtering

Abstract

The invention discloses an information recommendation method based on graph convolution and neural collaborative filtering. Combining the advantages of the graph convolutional neural network model, various information can be fused in an intuitive manner, and not only can receive user feature information, Moreover, it can receive user attribute information and has good recommendation performance for sparse scoring data; in addition, it uses a variety of techniques to optimize the model's input and parameters to overcome possible detailed problems. In addition, due to the introduction of a nonlinear neural network-based collaborative filtering method as the decoder part of the model, the user and item codes output by the graph convolutional encoder can be well utilized. Through the end‑to‑end model, all processes are It runs under the same framework and does not need to be trained separately. After processing the input data and training and predicting the model, a complete score prediction matrix can be obtained.

Description

technical field [0001] The invention relates to the technical field of information recommendation, in particular to an information recommendation method based on graph convolution and neural collaborative filtering. Background technique [0002] Since many online services on the Internet can give users a wealth of choices, providing high-precision and personalized recommendation results has been generally considered to be the cornerstone of many important applications on the Internet, such as the recommendation of machine learning methods in entertainment, shopping, and academic fields. System (RS, RecommenderSystem). For individuals, using recommender systems allows users to acquire and utilize information in a more efficient manner. In addition, many companies have widely used recommendation system technology to locate target users by proactively recommending products or services. With the continuous progress of various machine learning techniques and data mining techniq...

AI Technical Summary

Problems solved by technology

In recent years, many deep learning-based methods try to fuse auxiliary information for recommendation, and have achieved performance improvements compared to traditional methods, but few models can handle graph structure information

The existing collaborative filtering work based on graph convolution is still based on the traditional matrix decomposition method, using the method of linear inner product calculation to combine the encoding vectors, and predicting ratings in this way will also lead to a decrease in recommendation performance

However, the existing nonlinear neural collaborative filtering (NCF, NEURAL COLLABORATIVE FILTERING) uses a nonlinear neural network for the collaborative filtering process, but the auxiliary information is not considered in the model recommendation process, so it cannot make good use of auxiliary information and scoring. Information makes predictions on unknown ratings

The above problems have restricted the development of recommender system models.

Images