gammagl.layers.conv.FILMConv

class FILMConv(in_channels, out_channels, num_relations=1, act=ReLU<>)

The FiLM graph convolutional operator from the “GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation” paper

\[\mathbf{x}^{\prime}_i = \sum_{r \in \mathcal{R}} \sum_{j \in \mathcal{N}(i)} \sigma \left( \boldsymbol{\gamma}_{r,i} \odot \mathbf{W}_r \mathbf{x}_j + \boldsymbol{\beta}_{r,i} \right)\]

where \(\boldsymbol{\beta}_{r,i}, \boldsymbol{\gamma}_{r,i} = g(\mathbf{x}_i)\) with \(g\) being a single linear layer by default. Self-loops are automatically added to the input graph and represented as its own relation type.

Parameters:

• in_channels (int, tuple) – Size of each input sample, or -1 to derive the size from the first input(s) to the forward method. A tuple corresponds to the sizes of source and target dimensionalities.

• out_channels (int) – Size of each output sample.

• num_relations (int, optional) – Number of relations. (default: 1)

• act (callable, optional) – Activation function \(\sigma\). (default: tlx.nn.ReLU())

forward(x, edge_index)

message(x, edge_index, beta, gamma, edge_weight=None)

Function that construct message from source nodes to destination nodes.

Parameters:

• x (tensor) – input node feature.

• edge_index (tensor) – edges from src to dst.

• edge_weight (tensor, optional) – weight of each edge.

Returns:

• tensor – output message

• Returns – the message matrix, and the shape is [num_edges, message_dim]