Abstract
The recommendation algorithm based on collaborative filtering is currently the most successful recommendation method. It recommends items to the user based on the known historical interaction data of the target user. Furthermore, the combination of the recommended algorithm based on collaborative filtration and other auxiliary knowledge base is an effective way to improve the performance of the recommended system, of which the Co-Factorization Model (<i>CoFM</i>) is one representative research. <i>CoFM</i>, a fusion recommendation model combining the collaborative filtering model <i>FM</i> and the graph embedding model <i>TransE</i>, introduces the information of many entities and their relations in the knowledge graph into the recommendation system as effective auxiliary information. It can effectively improve the accuracy of recommendations and alleviate the problem of sparse user historical interaction data. Unfortunately, the graph-embedded model <i>TransE</i> used in the <i>CoFM</i> model cannot solve the 1-N, N-1, and N-N problems well. To tackle this problem, a novel fusion recommendation model Joint Factorization Machines and <i>TransH</i> Model (<i>JFMH</i>) is proposed, which improves <i>CoFM</i> by replacing the <i>TransE</i> model with <i>TransH</i> model. A large number of experiments on two widely used benchmark data sets show that compared with <i>CoFM</i>, <i>JFMH</i> has improved performance in terms of item recommendation and knowledge graph completion, and is more competitive than multiple baseline methods.
Highlights
The combination of the recommended algorithm based on collaborative filtration and other auxiliary knowledge base is an effective way to improve the performance of the recommended system, of which the Co-Factorization Model (CoFM) is one representative research
Use FM to embed the user-item historical interaction information, and establish a graph representation model based on the TransH model to learn the knowledge graph, and use the graph embedding representation to supplement and strengthen the results of FM; 2) Use the acquired user-item historical interaction information to supplement the association relationships that may be missing in the knowledge graph; 3) Experiments on two data sets widely used in academia show the effectiveness of our method
The CKE model uses the TransR method based on graph embedding to combine the recommendation system with the knowledge graph, and CoFM, as the improvement basis of our model method, combines the FM based on collaborative filtering and the TransE model based on graph embedding
Summary
In an era of rapid development of the Internet, information explosion is a problem that we must face at present. The method based on collaborative filtering is a relatively successful practical case in the personalized recommendation algorithm [5–7] This type of algorithm efficiently completes the target task of the recommendation system, due to the relatively serious cold start problem, it is helpless when the interaction relationship between the user set U and the item set I is sparse. Use FM to embed the user-item historical interaction information, and establish a graph representation model based on the TransH model to learn the knowledge graph, and use the graph embedding representation to supplement and strengthen the results of FM; 2) Use the acquired user-item historical interaction information to supplement the association relationships that may be missing in the knowledge graph; 3) Experiments on two data sets widely used in academia show the effectiveness of our method
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have