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