Application of graph modeling and contrast learning in recommender system

HIGHLIGHTS

• What: In this paper a method of combining graph modeling and contrast learning is proposed to improve the performance of recommendation system by mining complex user project interaction and user preference. As the authors delve into the mechanisms of model performance improvement, the authors focus on how graph modeling and contrast learning work together for recommender systems. In the part of contrast learning, the authors design a two-tower structure to deal with the embedding vector of user and item respectively. From the point of view of mathematical model, this method guides the model to form more . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.