# TAGConvο

class dgl.nn.pytorch.conv.TAGConv(in_feats, out_feats, k=2, bias=True, activation=None)[source]ο

Bases: Module

$H^{K} = {\sum}_{k=0}^K (D^{-1/2} A D^{-1/2})^{k} X {\Theta}_{k},$

where $$A$$ denotes the adjacency matrix, $$D_{ii} = \sum_{j=0} A_{ij}$$ its diagonal degree matrix, $${\Theta}_{k}$$ denotes the linear weights to sum the results of different hops together.

Parameters:
• in_feats (int) β Input feature size. i.e, the number of dimensions of $$X$$.

• out_feats (int) β Output feature size. i.e, the number of dimensions of $$H^{K}$$.

• k (int, optional) β Number of hops $$K$$. Default: 2.

• bias (bool, optional) β If True, adds a learnable bias to the output. Default: True.

• activation (callable activation function/layer or None, optional) β If not None, applies an activation function to the updated node features. Default: None.

linο

The learnable linear module.

Type:

torch.Module

Example

>>> import dgl
>>> import numpy as np
>>> import torch as th
>>> from dgl.nn import TAGConv
>>>
>>> g = dgl.graph(([0,1,2,3,2,5], [1,2,3,4,0,3]))
>>> feat = th.ones(6, 10)
>>> conv = TAGConv(10, 2, k=2)
>>> res = conv(g, feat)
>>> res
tensor([[ 0.5490, -1.6373],
[ 0.5490, -1.6373],
[ 0.5490, -1.6373],
[ 0.5513, -1.8208],
[ 0.5215, -1.6044],

forward(graph, feat, edge_weight=None)[source]ο

## Descriptionο

param graph:

The graph.

type graph:

DGLGraph

param feat:

The input feature of shape $$(N, D_{in})$$ where $$D_{in}$$ is size of input feature, $$N$$ is the number of nodes.

type feat:

torch.Tensor

param edge_weight:

edge_weight to use in the message passing process. This is equivalent to using weighted adjacency matrix in the equation above, and $$\tilde{D}^{-1/2}\tilde{A} \tilde{D}^{-1/2}$$ is based on dgl.nn.pytorch.conv.graphconv.EdgeWeightNorm.

type edge_weight:

torch.Tensor, optional

returns:

The output feature of shape $$(N, D_{out})$$ where $$D_{out}$$ is size of output feature.

rtype:

torch.Tensor

reset_parameters()[source]ο

## Descriptionο

Reinitialize learnable parameters.

Note

The model parameters are initialized using Glorot uniform initialization.