2021-07-27

Pytorch Geometric 经典模型

https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html#models

GCN

The Graph Neural Network from the “Semi-supervised Classification with Graph Convolutional Networks” paper, using the GCNConv operator for message passing.

GraphSAGE

The Graph Neural Network from the “Inductive Representation Learning on Large Graphs” paper, using the SAGEConv operator for message passing.

GIN

The Graph Neural Network from the “How Powerful are Graph Neural Networks?” paper, using the GINConv operator for message passing.

GAT

The Graph Neural Network from the “Graph Attention Networks” paper, using the GATConv operator for message passing.

GAE

The Graph Auto-Encoder model from the “Variational Graph Auto-Encoders” paper based on user-defined encoder and decoder models.

VGAE

The Variational Graph Auto-Encoder model from the “Variational Graph Auto-Encoders” paper.

ARGA

The Adversarially Regularized Graph Auto-Encoder model from the “Adversarially Regularized Graph Autoencoder for Graph Embedding” paper.

ARGVA

The Adversarially Regularized Variational Graph Auto-Encoder model from the “Adversarially Regularized Graph Autoencoder for Graph Embedding” paper.

SignedGCN

The signed graph convolutional network model from the “Signed Graph Convolutional Network” paper.

RENet

The Recurrent Event Network model from the “Recurrent Event Network for Reasoning over Temporal Knowledge Graphs” paper

GraphUNet

The Graph U-Net model from the “Graph U-Nets” paper which implements a U-Net like architecture with graph pooling and unpooling operations.

GNNExplainer

The GNN-Explainer model from the “GNNExplainer: Generating Explanations for Graph Neural Networks” paper for identifying compact subgraph structures and small subsets node features that play a crucial role in a GNN’s node-predictions.

MetaPath2Vec

The MetaPath2Vec model from the “metapath2vec: Scalable Representation Learning for Heterogeneous Networks” paper where random walks based on a given metapath are sampled in a heterogeneous graph, and node embeddings are learned via negative sampling optimization.

DeepGCNLayer

The skip connection operations from the “DeepGCNs: Can GCNs Go as Deep as CNNs?” and “All You Need to Train Deeper GCNs” papers.

AttentiveFP

The Attentive FP model for molecular representation learning from the “Pushing the Boundaries of Molecular Representation for Drug Discovery with the Graph Attention Mechanism” paper, based on graph attention mechanisms.