Papers
Sign in to view your remaining parses.
Tag Filter
GNN-based Recommender Systems
LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
Published:2/6/2020
GNN-based Recommender SystemsLightGCN ModelNeighborhood AggregationUser-Item Interaction GraphImprovement in Collaborative Filtering
This study introduces LightGCN, simplifying Graph Convolutional Networks for recommendations. We found that common features like transformation and nonlinear activation added complexity with little performance gain. LightGCN focuses on neighborhood aggregation, achieving a notabl
04
Knowledge Graph Convolutional Networks for Recommender Systems
Published:3/19/2019
Knowledge Graph-based RecommendationGNN-based Recommender SystemsCold-Start ProblemHigh-Order Structural Information ModelingNeighbor Sampling Mechanism
KGCN uses neighbor sampling to capture highorder structural and semantic information in knowledge graphs, addressing sparsity and coldstart in recommender systems. It performs well on largescale datasets in movie, book, and music recommendations.
01