topobench.nn.encoders package

Init file for encoder module with automated encoder discovery.

class AllCellFeatureEncoder(in_channels, out_channels, proj_dropout=0, selected_dimensions=None, **kwargs)

Bases: AbstractFeatureEncoder

Encoder class to apply BaseEncoder.

The BaseEncoder is applied to the features of higher order structures. The class creates a BaseEncoder for each dimension specified in selected_dimensions. Then during the forward pass, the BaseEncoders are applied to the features of the corresponding dimensions.

Parameters:

in_channelslist[int]

Input dimensions for the features.

out_channelslist[int]

Output dimensions for the features.

proj_dropoutfloat, optional

Dropout for the BaseEncoders (default: 0).

selected_dimensionslist[int], optional

List of indexes to apply the BaseEncoders to (default: None).

**kwargsdict, optional

Additional keyword arguments.

__init__(in_channels, out_channels, proj_dropout=0, selected_dimensions=None, **kwargs)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(data)

Forward pass.

The method applies the BaseEncoders to the features of the selected_dimensions.

Parameters:

datatorch_geometric.data.Data

Input data object which should contain x_{i} features for each i in the selected_dimensions.

Returns:

torch_geometric.data.Data

Output data object with updated x_{i} features.

class DGMStructureFeatureEncoder(in_channels, out_channels, proj_dropout=0, selected_dimensions=None, **kwargs)

Bases: AbstractFeatureEncoder

Encoder class to apply BaseEncoder.

The BaseEncoder is applied to the features of higher order structures. The class creates a BaseEncoder for each dimension specified in selected_dimensions. Then during the forward pass, the BaseEncoders are applied to the features of the corresponding dimensions.

Parameters:

in_channelslist[int]

Input dimensions for the features.

out_channelslist[int]

Output dimensions for the features.

proj_dropoutfloat, optional

Dropout for the BaseEncoders (default: 0).

selected_dimensionslist[int], optional

List of indexes to apply the BaseEncoders to (default: None).

**kwargsdict, optional

Additional keyword arguments.

__init__(in_channels, out_channels, proj_dropout=0, selected_dimensions=None, **kwargs)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(data)

Forward pass.

The method applies the BaseEncoders to the features of the selected_dimensions.

Parameters:

datatorch_geometric.data.Data

Input data object which should contain x_{i} features for each i in the selected_dimensions.

Returns:

torch_geometric.data.Data

Output data object with updated x_{i} features.

class FlatEncoder(in_channels, out_channels, **kwargs)

Bases: AbstractFeatureEncoder

Abstract class to define a custom feature encoder.

Parameters:

in_channelsint

Number of input channels.

out_channelsint

Number of output channels.

**kwargs

Additional keyword arguments.

__init__(in_channels, out_channels, **kwargs)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(data)

Forward pass of the flat encoder.

Parameters:

datatorch_geometric.data.Data

Input data object which should contain x features.

Returns:

torch_geometric.data.Data

Output data object with flattened features.

class HOPSEFeatureEncoder(in_channels, out_channels, proj_dropout=0, selected_dimensions=None, max_hop=3, batch_norm=False, use_atom_encoder=False, use_bond_encoder=False, fuse_pse2cell=False, **kwargs)

Bases: AbstractFeatureEncoder

Encoder class to apply SimpleEncoder.

The SimpleEncoder is applied to the features of each cell according to a simple

Parameters:

in_channelslist[list[int]]

Input dimensions for the features.

out_channelslist[int]

Output dimensions for the features.

proj_dropoutfloat, optional

Dropout for the BaseEncoders (default: 0).

selected_dimensionslist[int], optional

List of indexes to apply the BaseEncoders to (default: None).

max_hoplist[int], optional

List of indexes to apply the BaseEncoders to in terms of hops (default: None).

batch_normbool, optional

Wether to apply batch normalizaiton when encoding (default: False).

use_atom_encoderbool, optional

If True, replace the encoder for dimension 0 / hop 0 with an OGB AtomEncoder (default: False).

use_bond_encoderbool, optional

If True, replace the encoder for dimension 1 / hop 0 with an OGB BondEncoder (default: False).

fuse_pse2cellbool, optional

If True, concatenate and linearly project per-hop PSE encodings back into the cell features after encoding (default: False).

**kwargsdict, optional

Additional keyword arguments.

__init__(in_channels, out_channels, proj_dropout=0, selected_dimensions=None, max_hop=3, batch_norm=False, use_atom_encoder=False, use_bond_encoder=False, fuse_pse2cell=False, **kwargs)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(data)

Forward pass.

The method applies the BaseEncoders to the features of the selected_dimensions.

Parameters:

datatorch_geometric.data.Data

Input data object which should contain x_{i} features for each i in the selected_dimensions.

Returns:

torch_geometric.data.Data

Output data object with updated x_{i} features.

Submodules

• topobench.nn.encoders.all_cell_encoder module
  • AbstractFeatureEncoder
    • AbstractFeatureEncoder.__init__()
    • AbstractFeatureEncoder.forward()
  • AllCellFeatureEncoder
    • AllCellFeatureEncoder.__init__()
    • AllCellFeatureEncoder.forward()
  • BaseEncoder
    • BaseEncoder.__init__()
    • BaseEncoder.forward()
  • GraphNorm
    • GraphNorm.__init__()
    • GraphNorm.forward()
    • GraphNorm.reset_parameters()
• topobench.nn.encoders.base module
  • AbstractFeatureEncoder
    • AbstractFeatureEncoder.__init__()
    • AbstractFeatureEncoder.forward()
  • abstractmethod()
• topobench.nn.encoders.dgm_encoder module
  • AbstractFeatureEncoder
    • AbstractFeatureEncoder.__init__()
    • AbstractFeatureEncoder.forward()
  • BaseEncoder
    • BaseEncoder.__init__()
    • BaseEncoder.forward()
  • DGMStructureFeatureEncoder
    • DGMStructureFeatureEncoder.__init__()
    • DGMStructureFeatureEncoder.forward()
  • DGM_d
    • DGM_d.__init__()
    • DGM_d.forward()
    • DGM_d.sample_without_replacement()
• topobench.nn.encoders.flat_encoder module
  • AbstractFeatureEncoder
    • AbstractFeatureEncoder.__init__()
    • AbstractFeatureEncoder.forward()
  • FlatEncoder
    • FlatEncoder.__init__()
    • FlatEncoder.forward()
• topobench.nn.encoders.hopse_encoder module
  • AbstractFeatureEncoder
    • AbstractFeatureEncoder.__init__()
    • AbstractFeatureEncoder.forward()
  • AtomEncoder
    • AtomEncoder.__init__()
    • AtomEncoder.forward()
  • BondEncoder
    • BondEncoder.__init__()
    • BondEncoder.forward()
  • HOPSEFeatureEncoder
    • HOPSEFeatureEncoder.__init__()
    • HOPSEFeatureEncoder.forward()
  • MLP
    • MLP.__init__()
    • MLP.forward()
    • MLP.reset_parameters()
    • MLP.in_channels
    • MLP.num_layers
    • MLP.out_channels
    • MLP.supports_norm_batch
  • SimpleAtomEncoder
    • SimpleAtomEncoder.__init__()
    • SimpleAtomEncoder.forward()
  • SimpleBondEncoder
    • SimpleBondEncoder.__init__()
    • SimpleBondEncoder.forward()
• topobench.nn.encoders.kdgm module
  • DGM_d
    • DGM_d.__init__()
    • DGM_d.forward()
    • DGM_d.sample_without_replacement()
  • pairwise_euclidean_distances()
  • pairwise_poincare_distances()