Simplicial Complex Net Layer.

class topomodelx.nn.simplicial.scone_layer.SCoNeLayer(in_channels: int, out_channels: int, update_func: Literal['relu', 'sigmoid', 'tanh'] = 'tanh')

Implementation of the SCoNe layer proposed in [1].

Parameters:

in_channelsint

Input dimension of features on each edge.

out_channelsint

Output dimension of features on each edge.

update_funcLiteral[‘relu’, ‘sigmoid’, ‘tanh’]

Update function to use when updating edge features.

Methods

add_module(name, module)	Adds a child module to the current module.
apply(fn)	Applies fn recursively to every submodule (as returned by .children()) as well as self.
bfloat16()	Casts all floating point parameters and buffers to bfloat16 datatype.
buffers([recurse])	Returns an iterator over module buffers.
children()	Returns an iterator over immediate children modules.
cpu()	Moves all model parameters and buffers to the CPU.
cuda([device])	Moves all model parameters and buffers to the GPU.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Sets the module in evaluation mode.
extra_repr()	Set the extra representation of the module
float()	Casts all floating point parameters and buffers to float datatype.
forward(x, incidence_1, incidence_2)	Forward pass.
get_buffer(target)	Returns the buffer given by target if it exists, otherwise throws an error.
get_extra_state()	Returns any extra state to include in the module's state_dict.
get_parameter(target)	Returns the parameter given by target if it exists, otherwise throws an error.
get_submodule(target)	Returns the submodule given by target if it exists, otherwise throws an error.
half()	Casts all floating point parameters and buffers to half datatype.
ipu([device])	Moves all model parameters and buffers to the IPU.
load_state_dict(state_dict[, strict])	Copies parameters and buffers from state_dict into this module and its descendants.
modules()	Returns an iterator over all modules in the network.
named_buffers([prefix, recurse, ...])	Returns an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
named_children()	Returns an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
named_modules([memo, prefix, remove_duplicate])	Returns an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
named_parameters([prefix, recurse, ...])	Returns an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters([recurse])	Returns an iterator over module parameters.
register_backward_hook(hook)	Registers a backward hook on the module.
register_buffer(name, tensor[, persistent])	Adds a buffer to the module.
register_forward_hook(hook, *[, prepend, ...])	Registers a forward hook on the module.
register_forward_pre_hook(hook, *[, ...])	Registers a forward pre-hook on the module.
register_full_backward_hook(hook[, prepend])	Registers a backward hook on the module.
register_full_backward_pre_hook(hook[, prepend])	Registers a backward pre-hook on the module.
register_load_state_dict_post_hook(hook)	Registers a post hook to be run after module's load_state_dict is called.
register_module(name, module)	Alias for add_module().
register_parameter(name, param)	Adds a parameter to the module.
register_state_dict_pre_hook(hook)	These hooks will be called with arguments: self, prefix, and keep_vars before calling state_dict on self.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
reset_parameters([gain])	Reset learnable parameters.
set_extra_state(state)	This function is called from load_state_dict() to handle any extra state found within the state_dict.
share_memory()	See torch.Tensor.share_memory_()
state_dict(*args[, destination, prefix, ...])	Returns a dictionary containing references to the whole state of the module.
to(*args, **kwargs)	Moves and/or casts the parameters and buffers.
to_empty(*, device)	Moves the parameters and buffers to the specified device without copying storage.
train([mode])	Sets the module in training mode.
type(dst_type)	Casts all parameters and buffers to dst_type.
xpu([device])	Moves all model parameters and buffers to the XPU.
zero_grad([set_to_none])	Sets gradients of all model parameters to zero.

__call__

Notes

This is the architecture proposed for trajectory prediction on simplicial complexes.

For the trajectory prediction architecture proposed in [1], these layers are stacked before applying the boundary map from 1-chains to 0-chains. Finally, one can apply the softmax operator on the neighbouring nodes of the last node in the given trajectory to predict the next node. When implemented like this, we get a map from (ordered) 1-chains (trajectories) to the neighbouring nodes of the last node in the 1-chain.

References

[1] (1,2)

Roddenberry, Mitchell, Glaze. Principled simplicial neural networks for trajectory prediction. ICML 2021. https://proceedings.mlr.press/v139/roddenberry21a.html

[2]

Papillon, Sanborn, Hajij, Miolane. Equations of topological neural networks (2023). awesome-tnns/awesome-tnns

[3]

Papillon, Sanborn, Hajij, Miolane. Architectures of topological deep learning: a survey on topological neural networks (2023). https://arxiv.org/abs/2304.10031.

forward(x: Tensor, incidence_1: Tensor, incidence_2: Tensor) → Tensor

Forward pass.

The forward pass was initially proposed in [1]_. Its equations are given in [2]_ and graphically illustrated in [3]_.

\[\begin{split}\begin{align*} &🟥 \quad m^{(1 \rightarrow 0 \rightarrow 1)}_{y \rightarrow \{z\} \rightarrow x} = (L_{\downarrow,1})_{xy} \cdot h_y^{t,(1)} \cdot \Theta^{t,(1 \rightarrow 0 \rightarrow 1)}\\ &🟥 \quad m_{x \rightarrow x}^{(1 \rightarrow 1)} = h_x^{t,(1)} \cdot \Theta^{t,(1 \rightarrow 1)}\\ &🟥 \quad m_{y \rightarrow \{z\} \rightarrow x}^{(1 \rightarrow 2 \rightarrow 1)} = (L_{\uparrow,1})_{xy} \cdot h_y^{t,(1)} \cdot \Theta^{t,(1 \rightarrow 2 \rightarrow 1)}\\ &🟧 \quad m_{x}^{(1 \rightarrow 0 \rightarrow 1)} = \sum_{y \in \mathcal{L}_\downarrow(x)} m_{y \rightarrow \{z\} \rightarrow x}^{(1 \rightarrow 0 \rightarrow 1)}\\ &🟧 \quad m_{x}^{(1 \rightarrow 2 \rightarrow 1)} = \sum_{y \in \mathcal{L}_\uparrow(x)} m_{y \rightarrow \{z\} \rightarrow x}^{(1 \rightarrow 2 \rightarrow 1)}\\ &🟩 \quad m_x^{(1)} = m_{x}^{(1 \rightarrow 0 \rightarrow 1)} + m_{x \rightarrow x}^{(1 \rightarrow 1)} + m_{x}^{(1 \rightarrow 2 \rightarrow 1)}\\ &🟦 \quad h_x^{t,(1)} = \sigma(m_x^{(1)}) \end{align*}\end{split}\]

Parameters:

x: torch.Tensor, shape = (n_edges, in_channels)

Input features on the edges of the simplicial complex.

incidence_1torch.sparse, shape = (n_nodes, n_edges)

Incidence matrix \(B_1\) mapping edges to nodes.

incidence_2torch.sparse, shape = (n_edges, n_triangles)

Incidence matrix \(B_2\) mapping triangles to edges.

Returns:

torch.Tensor, shape = (n_edges, out_channels)

Output features on the edges of the simplicial complex.

reset_parameters(gain: float = 1.0) → None

Reset learnable parameters.