Simplified PCNet with Robustness

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.

CDC: A Simple Framework for Complex Data Clustering

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.

Attribute Clustering +1

Provable Filter for Real-world Graph Clustering

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.

Clustering Graph Clustering

Robust Graph Structure Learning under Heterophily

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.

Graph Representation Learning Graph structure learning