From Content Text Encoding Perspective: A Hybrid Deep Matrix Factorization Approach for Recommender System.
Jianing ZhouJunhao WenShun LiWei ZhouPublished in: IJCNN (2019)
Keyphrases
- matrix factorization
- recommender systems
- collaborative filtering
- user generated content
- low rank
- implicit feedback
- user interests
- cold start problem
- negative matrix factorization
- factor analysis
- nonnegative matrix factorization
- factorization methods
- data sparsity
- user preferences
- web documents
- variational bayesian
- information retrieval
- recommendation quality
- stochastic gradient descent
- item recommendation
- keywords
- missing data
- user generated
- recommendation systems
- web content
- cold start
- latent factors
- tensor factorization
- personalized ranking
- personalized recommendation
- user ratings
- user experience
- text documents
- user profiles
- least squares
- probabilistic matrix factorization