Graph Neural Network

Do We Really Need Graph Convolution During Training? Light Post-Training Graph-ODE for Efficient Recommendation
The efficiency and scalability of graph convolution networks (GCNs) in training recommender systems (RecSys) have been persistent …
Weizhi Zhang, Liangwei Yang, Zihe Song, Henry Peng Zhou, Ke Xu, Liancheng Fang, Philip S. Yu
PDF Cite