no code implementations • 23 Jun 2023 • Chenxuan Xie, Jiajun Zhou, Shengbo Gong, Jiacheng Wan, Jiaxu Qian, Shanqing Yu, Qi Xuan, Xiaoniu Yang
However, common practices in GNNs to acquire high-order information mainly through increasing model depth and altering message-passing mechanisms, which, albeit effective to a certain extent, suffer from three shortcomings: 1) over-smoothing due to excessive model depth and propagation times; 2) high-order information is not fully utilized; 3) low computational efficiency.
no code implementations • 4 Jun 2023 • Jiajun Zhou, Shengbo Gong, Chenxuan Xie, Shanqing Yu, Qi Xuan, Xiaoniu Yang
A minority of studies attempt to train different node groups separately but suffer from inappropriate separation metrics and low efficiency.
1 code implementation • 24 Jan 2023 • Shengbo Gong, Jiajun Zhou, Chenxuan Xie, Qi Xuan
Graph neural networks (GNNs) have been proved powerful in graph-oriented tasks.
1 code implementation • 20 Dec 2022 • Jiajun Zhou, Chenxuan Xie, Zhenyu Wen, Xiangyu Zhao, Qi Xuan
In recent years, graph representation learning has achieved remarkable success while suffering from low-quality data problems.