1 code implementation • 9 Feb 2024 • Xunkai Li, Jingyuan Ma, Zhengyu Wu, Daohan Su, Wentao Zhang, Rong-Hua Li, Guoren Wang
However, (i) Most scalable GNNs tend to treat all nodes in graphs with the same propagation rules, neglecting their topological uniqueness; (ii) Existing node-wise propagation optimization strategies are insufficient on web-scale graphs with intricate topology, where a full portrayal of nodes' local properties is required.
1 code implementation • 22 Jan 2024 • Xunkai Li, Meihao Liao, Zhengyu Wu, Daohan Su, Wentao Zhang, Rong-Hua Li, Guoren Wang
Most existing graph neural networks (GNNs) are limited to undirected graphs, whose restricted scope of the captured relational information hinders their expressive capabilities and deployments in real-world scenarios.
no code implementations • 7 Dec 2023 • Henan Sun, Xunkai Li, Zhengyu Wu, Daohan Su, Rong-Hua Li, Guoren Wang
Despite numerous attempts, most existing GNNs struggle to achieve optimal node representations due to the constraints of undirected graphs.
Ranked #28 on Node Classification on Cornell