no code implementations • 6 Mar 2024 • Bingheng Li, Xuanting Xie, Haoxiang Lei, Ruiyi Fang, Zhao Kang
Graph Neural Networks (GNNs) have garnered significant attention for their success in learning the representation of homophilic or heterophilic graphs.
no code implementations • 6 Mar 2024 • Zhao Kang, Xuanting Xie, Bingheng Li, Erlin Pan
In particular, we deploy CDC to graph data of size 111M.
no code implementations • 6 Mar 2024 • Xuanting Xie, Erlin Pan, Zhao Kang, Wenyu Chen, Bingheng Li
Motivated by this finding, we construct two graphs that are highly homophilic and heterophilic, respectively.
no code implementations • 6 Mar 2024 • Xuanting Xie, Zhao Kang, Wenyu Chen
In this regard, we propose a novel robust graph structure learning method to achieve a high-quality graph from heterophilic data for downstream tasks.