TWIRLSUnfoldingAndAttention

class dgl.nn.pytorch.conv.TWIRLSUnfoldingAndAttention(d, alp, lam, prop_step, attn_aft=-1, tau=0.2, T=-1, p=1, use_eta=False, init_att=False, attn_dropout=0, precond=True)[source]

Bases: torch.nn.modules.module.Module

Combine propagation and attention together.

Parameters
  • d (int) – Size of graph feature.

  • alp (float) – Step size. \(\alpha\) in ther paper.

  • lam (int) – Coefficient of graph smooth term. \(\lambda\) in ther paper.

  • prop_step (int) – Number of propagation steps

  • attn_aft (int) – Where to put attention layer. i.e. number of propagation steps before attention. If set to -1, then no attention.

  • tau (float) – The lower thresholding parameter. Correspond to \(\tau\) in the paper.

  • T (float) – The upper thresholding parameter. Correspond to \(T\) in the paper.

  • p (float) – Correspond to \(\rho\) in the paper..

  • use_eta (bool) – If True, learn a weight vector for each dimension when doing attention.

  • init_att (bool) – If True, add an extra attention layer before propagation.

  • attn_dropout (float) – the dropout rate of attention value. Default: 0.0.

  • precond (bool) – If True, use pre-conditioned & reparameterized version propagation (eq.28), else use normalized laplacian (eq.30).

Example

>>> import dgl
>>> from dgl.nn import TWIRLSUnfoldingAndAttention
>>> import torch as th
>>> g = dgl.graph(([0, 1, 2, 3, 2, 5], [1, 2, 3, 4, 0, 3])).add_self_loop()
>>> feat = th.ones(6,5)
>>> prop = TWIRLSUnfoldingAndAttention(10, 1, 1, prop_step=3)
>>> res = prop(g,feat)
>>> res
tensor([[2.5000, 2.5000, 2.5000, 2.5000, 2.5000],
        [2.5000, 2.5000, 2.5000, 2.5000, 2.5000],
        [2.5000, 2.5000, 2.5000, 2.5000, 2.5000],
        [3.7656, 3.7656, 3.7656, 3.7656, 3.7656],
        [2.5217, 2.5217, 2.5217, 2.5217, 2.5217],
        [4.0000, 4.0000, 4.0000, 4.0000, 4.0000]])
forward(g, X)[source]

Compute forward pass of propagation & attention.

Parameters
  • g (DGLGraph) – The graph.

  • X (torch.Tensor) – Init features.

Returns

The graph.

Return type

torch.Tensor