class FiLMConv(in_channels: Union[int, Tuple[int, int]], out_channels: int, num_relations: int = 1, nn: Optional[Callable] = None, act: Optional[Callable] = ReLU(), aggr: str = 'mean', **kwargs)[source]

Bases: MessagePassing

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.


For an example of using FiLM, see examples/

  • in_channels (int or 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)

  • nn (torch.nn.Module, optional) – The neural network \(g\) that maps node features x_i of shape [-1, in_channels] to shape [-1, 2 * out_channels]. If set to None, \(g\) will be implemented as a single linear layer. (default: None)

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

  • aggr (str, optional) – The aggregation scheme to use ("add", "mean", "max"). (default: "mean")

  • **kwargs (optional) – Additional arguments of torch_geometric.nn.conv.MessagePassing.

  • input: node features \((|\mathcal{V}|, F_{in})\) or \(((|\mathcal{V_s}|, F_{s}), (|\mathcal{V_t}|, F_{t}))\) if bipartite, edge indices \((2, |\mathcal{E}|)\), edge types \((|\mathcal{E}|)\)

  • output: node features \((|\mathcal{V}|, F_{out})\) or \((|\mathcal{V_t}|, F_{out})\) if bipartite

forward(x: Union[Tensor, Tuple[Tensor, Tensor]], edge_index: Union[Tensor, SparseTensor], edge_type: Optional[Tensor] = None) Tensor[source]

Runs the forward pass of the module.


Resets all learnable parameters of the module.