Layer

openhgnn.layers.HeteroEmbedLayer	Embedding layer for featureless heterograph.
openhgnn.layers.GeneralLinear	General Linear, combined with activation, normalization(batch and L2), dropout and so on.
openhgnn.layers.HeteroLinearLayer	Transform feature with nn.Linear.
openhgnn.layers.HeteroMLPLayer	HeteroMLPLayer contains multiple GeneralLinears, different with HeteroLinearLayer.
openhgnn.layers.HeteroFeature	This is a feature preprocessing component which is dealt with various heterogeneous feature situation.
openhgnn.layers.MetapathConv	MetapathConv is an aggregation function based on meta-path, which is similar with dgl.nn.pytorch.HeteroGraphConv.
openhgnn.layers.HeteroGraphConv	A generic module for computing convolution on heterogeneous graphs.
openhgnn.layers.ATTConv	It is macro_layer of the models [HetGNN].
openhgnn.layers.MacroConv	param in_feats: Input feature size.
openhgnn.layers.SemanticAttention
openhgnn.layers.CompConv	Composition-based convolution was introduced in Composition-based Multi-Relational Graph Convolutional Networks and mathematically is defined as follows:
openhgnn.layers.AttConv	Attention-based convolution was introduced in Hybrid Micro/Macro Level Convolution for Heterogeneous Graph Learning and mathematically is defined as follows:
openhgnn.layers.LSTMConv	Aggregate the neighbors with LSTM