gammagl.layers

Convolutional Layers

gammagl.layers.conv.MessagePassing	Base class for creating message passing layers of the form
gammagl.layers.conv.GCNConv	The graph convolutional operator from the "Semi-supervised Classification with Graph Convolutional Networks" paper
gammagl.layers.conv.GATConv	The graph attentional operator from the "Graph Attention Networks" paper
gammagl.layers.conv.SGConv	The simple graph convolutional operator from the "Simplifying Graph Convolutional Networks" paper
gammagl.layers.conv.SAGEConv	The GraphSAGE operator from the "Inductive Representation Learning on Large Graphs" paper
gammagl.layers.conv.GATV2Conv	The GATv2 operator from the "How Attentive are Graph Attention Networks?" paper, which fixes the static attention problem of the standard GATConv layer: since the linear layers in the standard GAT are applied right after each other, the ranking of attended nodes is unconditioned on the query node.
gammagl.layers.conv.GCNIIConv	The graph convolutional operator with initial residual connections and identity mapping (GCNII) from the "Simple and Deep Graph Convolutional Networks" paper
gammagl.layers.conv.APPNPConv	Approximate personalized propagation of neural predictions
gammagl.layers.conv.RGCNConv	The relational graph convolutional operator from the "Modeling Relational Data with Graph Convolutional Networks" paper
gammagl.layers.conv.AGNNConv	The graph attention operator from the "Attention-based Graph Neural Network for Semi-supervised Learning" paper
gammagl.layers.conv.JumpingKnowledge	The Jumping Knowledge layer aggregation module from the "Representation Learning on Graphs with Jumping Knowledge Networks" paper based on either
gammagl.layers.conv.HANConv	The Heterogenous Graph Attention Operator from the "Heterogenous Graph Attention Network" paper.
gammagl.layers.conv.ChebConv	The chebyshev spectral graph convolutional operator from the "Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering" paper
gammagl.layers.conv.HeteroConv	A generic wrapper for computing graph convolution on heterogeneous graphs.
gammagl.layers.conv.SimpleHGNConv	The SimpleHGN layer from the "Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks" paper
gammagl.layers.conv.FAGCNConv	The Frequency Adaptive Graph Convolution operator from the "Beyond Low-Frequency Information in Graph Convolutional Networks" paper
gammagl.layers.conv.GPRConv	The graph propagation oeprator from the "Adaptive Universal Generalized PageRank Graph Neural Network" paper
gammagl.layers.conv.HGTConv	The Heterogeneous Graph Transformer (HGT) operator from the "Heterogeneous Graph Transformer" paper.
gammagl.layers.conv.MixHopConv	The sparsified neighborhood mixing graph convolutional operator from the "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" paper
gammagl.layers.conv.HardGATConv	The graph hard attentional operator from the "Graph Representation Learning via Hard and Channel-Wise Attention Networks" paper
gammagl.layers.conv.PNAConv	The Principal Neighbourhood Aggregation graph convolution operator from the "Principal Neighbourhood Aggregation for Graph Nets" paper
gammagl.layers.conv.FILMConv	The FiLM graph convolutional operator from the "GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation" paper
gammagl.layers.conv.CompConv	Paper: Composition-based Multi-Relational Graph Convolutional Networks
gammagl.layers.conv.EdgeConv	The Edge Convolution operator from the "Dynamic Graph CNN for Learning on Point Clouds" paper
gammagl.layers.conv.HPNConv	The Heterogeneous Graph Propagation Operator from the "Heterogeneous Graph Propagation Network" paper.
gammagl.layers.conv.GINConv	The graph isomorphism operator from the "How Powerful are Graph Neural Networks?" paper
gammagl.layers.conv.HypergraphConv
gammagl.layers.conv.GMMConv	The Gaussian Mixture Model Convolution or MoNet operator from the "Geometric deep learning on graphs and manifolds using mixture model CNNs" paper
gammagl.layers.conv.ieHGCNConv	ie-HGCN from paper Interpretable and Efficient Heterogeneous Graph Convolutional Network.
gammagl.layers.conv.MGNNI_m_iter	The mgnni operator from the "Multiscale Graph Neural Networks with Implicit Layers" paper
gammagl.layers.conv.MAGCLConv	The graph convolutional operator from the "MA-GCL: Model Augmentation Tricks for Graph Contrastive Learning" paper

Pooling Layers

gammagl.layers.pool.global_max_pool	Returns batch-wise graph-level-outputs by taking the channel-wise maximum across the node dimension, so that for a single graph \(\mathcal{G}_i\) its output is computed by
gammagl.layers.pool.global_min_pool	Returns batch-wise graph-level-outputs by taking the channel-wise minimum across the node dimension, so that for a single graph \(\mathcal{G}_i\) its output is computed by
gammagl.layers.pool.global_mean_pool	Returns batch-wise graph-level-outputs by averaging node features across the node dimension, so that for a single graph \(\mathcal{G}_i\) its output is computed by
gammagl.layers.pool.global_sum_pool	Returns batch-wise graph-level-outputs by adding node features across the node dimension, so that for a single graph \(\mathcal{G}_i\) its output is computed by
gammagl.layers.pool.global_sort_pool	The global pooling operator from the "An End-to-End Deep Learning Architecture for Graph Classification" paper, where node features are sorted in descending order based on their last feature channel.

Model

gammagl.models.GCNModel	Graph Convolutional Network proposed in "Semi-supervised Classification with Graph Convolutional Networks" paper.
gammagl.models.GATModel	The graph attentional operator from the "Graph Attention Networks" paper.
gammagl.models.SGCModel	simplifing graph convoluation nerworks
gammagl.models.GATV2Model	"How Attentive are Graph Attention Networks?" paper.
gammagl.models.GraphSAGE_Full_Model
gammagl.models.GraphSAGE_Sample_Model	The GraphSAGE operator from the "Inductive Representation Learning on Large Graphs" paper
gammagl.models.GCNIIModel	The graph convolutional operator with initial residual connections and identity mapping (GCNII) from the "Simple and Deep Graph Convolutional Networks" paper.
gammagl.models.APPNPModel	Approximate personalized propagation of neural predictions
gammagl.models.GINModel	The FiLM graph convolutional operator from the "GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation" paper.
gammagl.models.RGCN	relational graph convoluation nerworks
gammagl.models.CompGCN	Composition-based Multi-Relational graph convoluation nerworks
gammagl.models.AGNNModel	The graph attention operator from the "Attention-based Graph Neural Network for Semi-supervised Learning" paper.
gammagl.models.JKNet
gammagl.models.HAN
gammagl.models.DGIModel	Deep Graph Infomax in DGL
gammagl.models.GraceModel
gammagl.models.ChebNetModel	Graph Convolutional Network proposed in "Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering" paper.
gammagl.models.SimpleHGNModel	This is a model SimpleHGN from Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks paper.
gammagl.models.FAGCNModel	The Frequency Adaptive Graph Convolution operator from the "Beyond Low-Frequency Information in Graph Convolutional Networks" paper.
gammagl.models.GPRGNNModel	Graph Convolutional Network proposed in "Adaptive Universal Generalized PageRank Graph Neural Network" paper.
gammagl.models.DGCNN	DGCNN proposed in "An End-to-End Deep Learning Architecture for Graph Classification" paper.
gammagl.models.MixHopModel	MixHop proposed in "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" paper.
gammagl.models.HCHA
gammagl.models.HGTModel	The Heterogeneous Graph Transformer (HGT) proposed in here paper.
gammagl.models.PNAModel
gammagl.models.HardGATModel	The graph hard attentional operator from the "Graph Representation Learning via Hard and Channel-Wise Attention Networks" paper.
gammagl.models.DGCNNModel	The Edge Convolution operator from the "Dynamic Graph CNN for Learning on Point Clouds" paper.
gammagl.models.FILMModel	The FiLM graph convolutional operator from the "GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation" paper.
gammagl.models.GEstimationN	Provide adjacency matrix estimation implementation based on the Expectation-Maximization(EM) algorithm.
gammagl.models.DeepWalkModel	The DeepWalk model from the "DeepWalk: Online Learning of Social Representations" paper where random walks of length walk_length are sampled in a given graph, and node embeddings are learned via negative sampling optimization.
gammagl.models.Node2vecModel	The Node2Vec model from the "node2vec: Scalable Feature Learning for Networks" paper where random walks of length walk_length are sampled in a given graph, and node embeddings are learned via negative sampling optimization.
gammagl.models.VGAEModel	Applications of Variational Encoders on Graphs proposed in Variational Graph Auto-Encoders paper.
gammagl.models.GAEModel	Applications of Auto-Encoders on Graphs proposed in "Variational Graph Auto-Encoders" paper.
gammagl.models.HPN	HPN proposed in "Heterogeneous Graph Propagation Network" paper.
gammagl.models.GMMModel	The Gaussian Mixture Model or MoNet from the "Geometric deep learning on graphs and manifolds using mixture model CNNs" paper.
gammagl.models.CAGCNModel	calibration GCN proposed in "Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration" paper.
gammagl.models.CoGSLModel	CoGSL Model proposed in '"Compact Graph Structure Learning via Mutual Information Compression" <https://arxiv.org/pdf/2201.05540.pdf>'_ paper.
gammagl.models.Specformer	The Specformer from the "Specformer:Spectral Graph Neural Networks Meet Transformers" paper