Item Graph Convolution Collaborative Filtering for Inductive Recommendations.
Edoardo D'AmicoKhalil MuhammadElias Z. TragosBarry SmythNeil HurleyAonghus LawlorPublished in: ECIR (1) (2023)
Keyphrases
- collaborative filtering
- making recommendations
- recommender systems
- personalized recommendation
- cold start problem
- hybrid recommendation
- user preferences
- user ratings
- cold start
- item recommendation
- recommendation algorithms
- latent factor models
- user similarity
- recommendation systems
- collaborative filtering recommendation algorithm
- data sparsity
- active user
- matrix factorization
- collaborative filtering algorithms
- recommendation quality
- random walk
- graph theory
- graph structure
- rating prediction
- collaborative recommendation
- online dating
- prediction accuracy
- pearson correlation coefficient
- collaborative filtering recommendation
- graph representation
- weighted graph
- graph theoretic
- directed graph
- image processing
- product recommendation
- inductive learning
- item based collaborative filtering
- directed acyclic graph
- connected components
- user behavior
- demographic information
- user profiles
- information filtering
- content based filtering
- graph model
- machine learning
- filtering algorithm
- social networks
- structured data
- collaborative filtering recommender systems
- functional programs
- inductive logic programming
- bipartite graph
- user interests
- information overload
- graph databases
- undirected graph