2 Hits in 1.4 sec

GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction [article]

Fenyu Hu, Yanqiao Zhu, Shu Wu, Weiran Huang, Liang Wang, Tieniu Tan
2020 arXiv   pre-print
Then, in order to better capture the complicated non-linearity of graph data, we present a novel GraphAIR framework which models the neighborhood interaction in addition to neighborhood aggregation.  ...  These GCNs generate node representation by aggregating features from the neighborhoods, which follows the "neighborhood aggregation" scheme.  ...  ACKNOWLEDGEMENTS This work is supported by National Natural Science Foundation of China (61772528) and National Key Research and Development Program (2018YFB1402600, 2016YFB1001000).  ... 
arXiv:1911.01731v3 fatcat:q2zl42m2gfdxpoap5ye3uoq4hq

Knowledge graph enhanced recommender system [article]

Zepeng Huai, Jianhua Tao, Feihu Che, Guohua Yang, Dawei Zhang
2021 arXiv   pre-print
In this paper, we proposed a novel attentive knowledge graph attribute network(AKGAN) to learn item attributes and user interests via attribute information in KG.  ...  Knowledge Graphs (KGs) have shown great success in recommendation. This is attributed to the rich attribute information contained in KG to improve item and user representations as side information.  ...  KGAT applies an attentive neighborhood aggregation mechanism on a holistic graph and introduces TransR to regularize the representations. • KGNN-LS [31] : It uses a user-specific relation scoring function  ... 
arXiv:2112.09425v1 fatcat:qej4svfjhbhfjmazhcowu5lboi