On the Equivalence of Decoupled Graph Convolution Network and Label Propagation
Hande Dong, Jiawei Chen, Fuli Feng, Xiangnan He, Shuxian Bi, Zhaolin Ding, Peng Cui
Abstract
The original design of Graph Convolution Network (GCN) couples feature transformation and neighborhood aggregation for node representation learning. Recently, some work shows that coupling is inferior to decoupling, which supports deep graph propagation better and has become the latest paradigm of GCN (e.g., APPNP [16] and SGCN [32]). Despite effectiveness, the working mechanisms of the decoupled GCN are not well understood.
Topics & Concepts
Computer scienceGraphTheoretical computer scienceConvolution (computer science)Decoupling (probability)Equivalence (formal languages)Representation (politics)Artificial intelligenceAlgorithmMathematicsDiscrete mathematicsArtificial neural networkEngineeringControl engineeringLawPoliticsPolitical scienceAdvanced Graph Neural NetworksRecommender Systems and TechniquesComplex Network Analysis Techniques