Feature Liftings#

Concatenation feature lifting.

class topobenchmarkx.transforms.feature_liftings.concatenation.Concatenation(**kwargs)[source]#

Lift r-cell features to r+1-cells by concatenation.

Parameters:

**kwargsoptional: Additional arguments for the class.

forward(data: Data | dict) → Data | dict[source]#

Apply the lifting to the input data.

Parameters:

datatorch_geometric.data.Data | dict: The input data to be lifted.

Returns:

torch_geometric.data.Data | dict: The lifted data.

lift_features(data: Data | dict) → Data | dict[source]#

Concatenate r-cell features to obtain r+1-cell features.

Parameters:

datatorch_geometric.data.Data | dict: The input data to be lifted.

Returns:

torch_geometric.data.Data | dict: The lifted data.

Identity transform that does nothing to the input data.

class topobenchmarkx.transforms.feature_liftings.identity.Identity(**kwargs)[source]#

An identity transform that does nothing to the input data.

Parameters:

**kwargsoptional: Parameters for the base transform.

forward(data: Data)[source]#

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data: The input data.

Returns:

torch_geometric.data.Data: The same data.

ProjectionSum class.

class topobenchmarkx.transforms.feature_liftings.projection_sum.ProjectionSum(**kwargs)[source]#

Lift r-cell features to r+1-cells by projection.

Parameters:

**kwargsoptional: Additional arguments for the class.

forward(data: Data | dict) → Data | dict[source]#

Apply the lifting to the input data.

Parameters:

datatorch_geometric.data.Data | dict: The input data to be lifted.

Returns:

torch_geometric.data.Data | dict: The lifted data.

lift_features(data: Data | dict) → Data | dict[source]#

Project r-cell features of a graph to r+1-cell structures.

Parameters:

datatorch_geometric.data.Data | dict: The input data to be lifted.

Returns:

torch_geometric.data.Data | dict: The data with the lifted features.

Set lifting for r-cell features to r+1-cell features.

class topobenchmarkx.transforms.feature_liftings.set.Set(**kwargs)[source]#

Lift r-cell features to r+1-cells by set operations.

Parameters:

**kwargsoptional: Additional arguments for the class.

forward(data: Data | dict) → Data | dict[source]#

Apply the lifting to the input data.

Parameters:

datatorch_geometric.data.Data | dict: The input data to be lifted.

Returns:

torch_geometric.data.Data | dict: The lifted data.

lift_features(data: Data | dict) → Data | dict[source]#

Concatenate r-cell features to r+1-cell structures.

Parameters:

datatorch_geometric.data.Data | dict: The input data to be lifted.

Returns:

torch_geometric.data.Data | dict: The lifted data.