Graphgallery 0.1.4
Frist stable version of Graphgallery, the following models are implemented:
General models
- GCN from Semi-Supervised Classification with Graph Convolutional Networks 🌐Paper
- GAT from Graph Attention Networks 🌐Paper
- SGC from Simplifying Graph Convolutional Networks 🌐Paper
- GraphSAGE from Inductive Representation Learning on Large Graphs 🌐Paper
- GWNN from Graph Wavelet Neural Network 🌐Paper
- GMNN from Graph Markov Neural Networks 🌐Paper
- ChebyNet from Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering 🌐Paper
- ClusterGCN from Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks 🌐Paper
- FastGCN from FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling 🌐Paper
- LGCN from Large-Scale Learnable Graph Convolutional Networks 🌐Paper
Defense models
- RGCN from Robust Graph Convolutional Networks Against Adversarial Attacks 🌐Paper
- SBVAT/OBVAT from Batch Virtual Adversarial Training for Graph Convolutional Networks 🌐Paper
Other models
- GCN_MIX: Mixture of GCN and MLP
- GCNF: GCN + feature
- DenseGCN: Dense version of GCN
- EdgeGCN: GCN using message passing framework
- MedianSAGE: GraphSAGE using
Medianaggregation