easygraph.model.hypergraphs package

Submodules

easygraph.model.hypergraphs.dhcf module

class easygraph.model.hypergraphs.dhcf.DHCF(num_users: int, num_items: int, emb_dim: int, num_layers: int = 3, drop_rate: float = 0.5)[source]

Bases: Module

The DHCF model proposed in Dual Channel Hypergraph Collaborative Filtering paper (KDD 2020).

Note

The user and item embeddings and trainable parameters are initialized with xavier_uniform distribution.

Parameters:

  • num_users (int) – The Number of users.

  • num_items (int) – The Number of items.

  • emb_dim (int) – Embedding dimension.

  • num_layers (int) – The Number of layers. Defaults to 3.

  • drop_rate (float) – The dropout probability. Defaults to 0.5.

forward(hg_ui: Hypergraph, hg_iu: Hypergraph) → Tuple[Tensor, Tensor][source]

The forward function.

Parameters:

  • hg_ui (eg.Hypergraph) – The hypergraph structure that users as vertices.

  • hg_iu (eg.Hypergraph) – The hypergraph structure that items as vertices.

reset_parameters()[source]

Initialize learnable parameters.

training: bool

easygraph.model.hypergraphs.dhne module

easygraph.model.hypergraphs.hgnn module

class easygraph.model.hypergraphs.hgnn.HGNN(in_channels: int, hid_channels: int, num_classes: int, use_bn: bool = False, drop_rate: float = 0.5)[source]

Bases: Module

The HGNN model proposed in Hypergraph Neural Networks paper (AAAI 2019).

Parameters:

  • in_channels (int) – \(C_{in}\) is the number of input channels.

  • hid_channels (int) – \(C_{hid}\) is the number of hidden channels.

  • num_classes (int) – The Number of class of the classification task.

  • use_bn (bool) – If set to True, use batch normalization. Defaults to False.

  • drop_rate (float, optional) – Dropout ratio. Defaults to 0.5.

forward(X: Tensor, hg: Hypergraph) → Tensor[source]

The forward function.

Parameters:

  • X (torch.Tensor) – Input vertex feature matrix. Size \((N, C_{in})\).

  • hg (eg.Hypergraph) – The hypergraph structure that contains \(N\) vertices.

training: bool

easygraph.model.hypergraphs.hgnnp module

class easygraph.model.hypergraphs.hgnnp.HGNNP(in_channels: int, hid_channels: int, num_classes: int, use_bn: bool = False, drop_rate: float = 0.5)[source]

Bases: Module

The HGNN + model proposed in HGNN+: General Hypergraph Neural Networks paper (IEEE T-PAMI 2022).

Parameters:

  • in_channels (int) – \(C_{in}\) is the number of input channels.

  • hid_channels (int) – \(C_{hid}\) is the number of hidden channels.

  • num_classes (int) – The Number of class of the classification task.

  • use_bn (bool) – If set to True, use batch normalization. Defaults to False.

  • drop_rate (float, optional) – Dropout ratio. Defaults to 0.5.

forward(X: Tensor, hg: eg.Hypergraph) → Tensor[source]

The forward function.

Parameters:

  • X (torch.Tensor) – Input vertex feature matrix. Size \((N, C_{in})\).

  • hg (eg.Hypergraph) – The hypergraph structure that contains \(N\) vertices.

training: bool

easygraph.model.hypergraphs.hnhn module

class easygraph.model.hypergraphs.hnhn.HNHN(in_channels: int, hid_channels: int, num_classes: int, use_bn: bool = False, drop_rate: float = 0.5)[source]

Bases: Module

The HNHN model proposed in HNHN: Hypergraph Networks with Hyperedge Neurons paper (ICML 2020).

Parameters:

  • in_channels (int) – \(C_{in}\) is the number of input channels.

  • hid_channels (int) – \(C_{hid}\) is the number of hidden channels.

  • num_classes (int) – The Number of class of the classification task.

  • use_bn (bool) – If set to True, use batch normalization. Defaults to False.

  • drop_rate (float, optional) – Dropout ratio. Defaults to 0.5.

forward(X: Tensor, hg: eg.Hypergraph) → Tensor[source]

The forward function.

Parameters:

  • X (torch.Tensor) – Input vertex feature matrix. Size \((N, C_{in})\).

  • hg (eg.Hypergraph) – The hypergraph structure that contains \(N\) vertices.

training: bool

easygraph.model.hypergraphs.hypergcn module

class easygraph.model.hypergraphs.hypergcn.HyperGCN(in_channels: int, hid_channels: int, num_classes: int, use_mediator: bool = False, use_bn: bool = False, fast: bool = True, drop_rate: float = 0.5)[source]

Bases: Module

The HyperGCN model proposed in HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs paper (NeurIPS 2019).

Parameters:

  • in_channels (int) – \(C_{in}\) is the number of input channels.

  • hid_channels (int) – \(C_{hid}\) is the number of hidden channels.

  • num_classes (int) – The Number of class of the classification task.

  • use_mediator (str) – Whether to use mediator to transform the hyperedges to edges in the graph. Defaults to False.

  • fast (bool) – If set to True, the transformed graph structure will be computed once from the input hypergraph and vertex features, and cached for future use. Defaults to True.

  • drop_rate (float, optional) – Dropout ratio. Defaults to 0.5.

forward(X: Tensor, hg: eg.Hypergraph) → Tensor[source]

The forward function.

Parameters:

  • X (torch.Tensor) – Input vertex feature matrix. Size \((N, C_{in})\).

  • hg (eg.Hypergraph) – The hypergraph structure that contains \(N\) vertices.

training: bool

easygraph.model.hypergraphs.setgnn module

easygraph.model.hypergraphs.unignn module

class easygraph.model.hypergraphs.unignn.UniGAT(in_channels: int, hid_channels: int, num_classes: int, num_heads: int, use_bn: bool = False, drop_rate: float = 0.5, atten_neg_slope: float = 0.2)[source]

Bases: Module

The UniGAT model proposed in UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks paper (IJCAI 2021).

Parameters:

  • in_channels (int) – \(C_{in}\) is the number of input channels.

  • hid_channels (int) – \(C_{hid}\) is the number of hidden channels.

  • num_classes (int) – The Number of class of the classification task.

  • num_heads (int) – The Number of attention head in each layer.

  • use_bn (bool) – If set to True, use batch normalization. Defaults to False.

  • drop_rate (float) – The dropout probability. Defaults to 0.5.

  • atten_neg_slope (float) – Hyper-parameter of the LeakyReLU activation of edge attention. Defaults to 0.2.

forward(X: Tensor, hg: eg.Hypergraph) → Tensor[source]

The forward function.

Parameters:

  • X (torch.Tensor) – Input vertex feature matrix. Size \((N, C_{in})\).

  • hg (eg.Hypergraph) – The hypergraph structure that contains \(N\) vertices.

training: bool
class easygraph.model.hypergraphs.unignn.UniGCN(in_channels: int, hid_channels: int, num_classes: int, use_bn: bool = False, drop_rate: float = 0.5)[source]

Bases: Module

The UniGCN model proposed in UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks paper (IJCAI 2021).

Parameters:

  • in_channels (int) – \(C_{in}\) is the number of input channels.

  • hid_channels (int) – \(C_{hid}\) is the number of hidden channels.

  • num_classes (int) – The Number of class of the classification task.

  • use_bn (bool) – If set to True, use batch normalization. Defaults to False.

  • drop_rate (float, optional) – Dropout ratio. Defaults to 0.5.

forward(X: Tensor, hg: eg.Hypergraph) → Tensor[source]

The forward function.

Parameters:

  • X (torch.Tensor) – Input vertex feature matrix. Size \((N, C_{in})\).

  • hg (eg.Hypergraph) – The hypergraph structure that contains \(N\) vertices.

training: bool
class easygraph.model.hypergraphs.unignn.UniGIN(in_channels: int, hid_channels: int, num_classes: int, eps: float = 0.0, train_eps: bool = False, use_bn: bool = False, drop_rate: float = 0.5)[source]

Bases: Module

The UniGIN model proposed in UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks paper (IJCAI 2021).

Parameters:

  • in_channels (int) – \(C_{in}\) is the number of input channels.

  • hid_channels (int) – \(C_{hid}\) is the number of hidden channels.

  • num_classes (int) – The Number of class of the classification task.

  • eps (float) – The epsilon value. Defaults to 0.0.

  • train_eps (bool) – If set to True, the epsilon value will be trainable. Defaults to False.

  • use_bn (bool) – If set to True, use batch normalization. Defaults to False.

  • drop_rate (float, optional) – Dropout ratio. Defaults to 0.5.

forward(X: Tensor, hg: eg.Hypergraph) → Tensor[source]

The forward function.

Parameters:

  • X (torch.Tensor) – Input vertex feature matrix. Size \((N, C_{in})\).

  • hg (eg.Hypergraph) – The hypergraph structure that contains \(N\) vertices.

training: bool
class easygraph.model.hypergraphs.unignn.UniSAGE(in_channels: int, hid_channels: int, num_classes: int, use_bn: bool = False, drop_rate: float = 0.5)[source]

Bases: Module

The UniSAGE model proposed in UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks paper (IJCAI 2021).

Parameters:

  • in_channels (int) – \(C_{in}\) is the number of input channels.

  • hid_channels (int) – \(C_{hid}\) is the number of hidden channels.

  • num_classes (int) – The Number of class of the classification task.

  • use_bn (bool) – If set to True, use batch normalization. Defaults to False.

  • drop_rate (float, optional) – Dropout ratio. Defaults to 0.5.

forward(X: Tensor, hg: eg.Hypergraph) → Tensor[source]

The forward function.

Parameters:

  • X (torch.Tensor) – Input vertex feature matrix. Size \((N, C_{in})\).

  • hg (eg.Hypergraph) – The hypergraph structure that contains \(N\) vertices.

training: bool

Module contents