gammagl.transforms.BaseTransform
|
An abstract base class for writing transforms. |
gammagl.transforms.AddMetaPaths
|
Adds additional edge types to a HeteroGraph object between the source node type and the destination node type of a given metapath , as described in the "Heterogenous Graph Attention Networks" paper. |
gammagl.transforms.Compose
|
Composes several transforms together. |
gammagl.transforms.SIGN
|
The Scalable Inception Graph Neural Network module (SIGN) from the "SIGN: Scalable Inception Graph Neural Networks" paper (functional name: sign ), which precomputes the fixed representations |
gammagl.transforms.NormalizeFeatures
|
Row-normalizes the attributes given in attrs to sum-up to one (functional name: normalize_features ). |
gammagl.transforms.DropEdge
|
Randomly drop edges, as described in DropEdge: Towards Deep Graph Convolutional Networks on Node Classification paper. |
gammagl.transforms.RandomLinkSplit
|
Performs an edge-level random split into training, validation and test sets of a Graph or a HeteroGraph object (functional name: random_link_split ). |
gammagl.transforms.mask_test_edges
|
|
gammagl.transforms.sparse_to_tuple
|
|