dynedge_kaggle_tito

Implementation of DynEdge architecture used in.

IceCube - Neutrinos in Deep Ice

Reconstruct the direction of neutrinos from the Universe to the South Pole

Kaggle competition.

Solution by TITO.

class graphnet.models.gnn.dynedge_kaggle_tito.DynEdgeTITO(*args, **kwargs)[source]

Bases: GNN

DynEdgeTITO (dynamical edge convolutional with Transformer) model.

Construct DynEdgeTITO.

Parameters:

  • nb_inputs (int) – Number of input features on each node.

  • features_subset (Optional[List[int]], default: None) – The subset of latent features on each node that are used as metric dimensions when performing the k-nearest neighbours clustering. Defaults to [0,1,2,3].

  • dyntrans_layer_sizes (Optional[List[Tuple[int, ...]]], default: None) – The layer sizes, or latent feature dimenions, used in the DynTrans layer. Defaults to [(256, 256), (256, 256), (256, 256), (256, 256)].

  • global_pooling_schemes (List[str], default: ['max']) – The list global pooling schemes to use. Options are: “min”, “max”, “mean”, and “sum”.

  • use_global_features (bool, default: True) – Whether to use global features after pooling.

  • use_post_processing_layers (bool, default: True) – Whether to use post-processing layers after the DynTrans layers.

  • post_processing_layer_sizes (Optional[List[int]], default: None) – The layer sizes used in the post-processing layers. Defaults to [336, 256].

  • readout_layer_sizes (Optional[List[int]], default: None) – The layer sizes used in the readout layers. Defaults to [256, 128].

  • n_head (int, default: 8) – The number of heads to use in the DynTrans layer.

  • nb_neighbours (int, default: 8) – The number of neighbours to use in the DynTrans layer.

  • args (Any)

  • kwargs (Any)

Return type:

object

forward(data)[source]

Apply learnable forward pass.

Return type:

Tensor

Parameters:

data (Data)