A spectral-based GCN for directed graphs uses redefined Laplacians to enable direct application to directed data and outperforms prior methods on semi-supervised node classification tasks.
Convolutional neural networks on graphs with fast localized spectral filtering
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2019 2verdicts
UNVERDICTED 2representative citing papers
NANG uses adversarial learning to generate unobserved node attributes from graph structure via a shared latent space.
citing papers explorer
-
Spectral-based Graph Convolutional Network for Directed Graphs
A spectral-based GCN for directed graphs uses redefined Laplacians to enable direct application to directed data and outperforms prior methods on semi-supervised node classification tasks.
-
Node Attribute Generation on Graphs
NANG uses adversarial learning to generate unobserved node attributes from graph structure via a shared latent space.