The topology adaptive graph convolutional networks operator from the "Topology Adaptive Graph Convolutional Networks" paper. The approximate personalized propagation of neural predictions layer from the "Predict then Propagate: Graph Neural Networks meet Personalized PageRank" paper. Applies layer normalization over each individual example in a batch of features as described in the "Layer Normalization" paper. The Heterogeneous Graph Transformer (HGT) operator from the "Heterogeneous Graph Transformer" paper.

The Graph Neural Network from the "Semi-supervised Classification with Graph Convolutional Networks" paper, using the GCNConv operator for message passing. The convolutional operator on \(\mathcal{X}\)-transformed points from the "PointCNN: Convolution On X-Transformed Points" paper. Conv2d module with lazy initialization of the in_channels argument of the Conv2d that is inferred from the input. The (translation-invariant) feature-steered convolutional operator from the "FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis" paper. Performs MLP aggregation in which the elements to aggregate are flattened into a single vectorial representation, and are then processed by a Multi-Layer Perceptron (MLP), as described in the "Graph Neural Networks with Adaptive Readouts" paper.GAT  class GAT ( in_channels : int, hidden_channels : int, num_layers : int, out_channels : Optional [ int ] = None, dropout : float = 0. Applies the Exponential Linear Unit (ELU) function, element-wise, as described in the paper: Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs). The PointNet set layer from the "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation" and "PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space" papers. A generic wrapper for computing graph convolution on directed graphs as described in the "Edge Directionality Improves Learning on Heterophilic Graphs" paper.

The dynamic edge convolutional operator from the "Dynamic Graph CNN for Learning on Point Clouds" paper (see torch_geometric.

Conv1d module with lazy initialization of the in_channels argument of the Conv1d that is inferred from the input. Combines one or more aggregators and transforms its output with one or more scalers as introduced in the "Principal Neighbourhood Aggregation for Graph Nets" paper.

The Graph Auto-Encoder model from the "Variational Graph Auto-Encoders" paper based on user-defined encoder and decoder models.Memory based pooling layer from "Memory-Based Graph Networks" paper, which learns a coarsened graph representation based on soft cluster assignments. The continuous-filter convolutional neural network SchNet from the "SchNet: A Continuous-filter Convolutional Neural Network for Modeling Quantum Interactions" paper that uses the interactions blocks of the form. Importantly, MultiAggregation provides various options to combine the outputs of its underlying aggegations ( e. ConvTranspose3d module with lazy initialization of the in_channels argument of the ConvTranspose3d that is inferred from the input.