Search Results for author:
Found 3 papers, 2 papers with code
Rethinking Node-wise Propagation for Large-scale Graph Learning
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.
LightDiC: A Simple yet Effective Approach for Large-scale Digraph Representation Learning
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.
Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification
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
