layers.py

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.nn.modules.module import Module
from torch.nn.parameter import Parameter


class GraphConvolution(Module):
    """
    Simple GCN layer, similar to https://arxiv.org/abs/1609.02907
    """

    def __init__(self, in_features, out_features, dropout=0., act=F.relu):
        super(GraphConvolution, self).__init__()
        self.in_features = in_features
        self.out_features = out_features
        self.dropout = dropout
        self.act = act
        self.weight = Parameter(torch.FloatTensor(in_features, out_features))
        self.reset_parameters()

    def reset_parameters(self):
        torch.nn.init.xavier_uniform_(self.weight)

    def forward(self, input, adj):
        input = F.dropout(input, self.dropout, self.training)
        support = torch.mm(input, self.weight)
        output = torch.spmm(adj, support)
        output = self.act(output)
        return output

    def __repr__(self):
        return self.__class__.__name__ + ' (' \
               + str(self.in_features) + ' -> ' \
               + str(self.out_features) + ')'


class GraphAttentionLayer(nn.Module):
    """
    Simple GAT layer, similar to https://arxiv.org/abs/1710.10903
    """

    def __init__(self, in_features, out_features, dropout, alpha, concat=True):
        super(GraphAttentionLayer, self).__init__()
        self.dropout = dropout
        self.in_features = in_features
        self.out_features = out_features
        self.alpha = alpha
        self.concat = concat

        self.W = nn.Parameter(torch.zeros(size=(in_features, out_features)))
        nn.init.xavier_uniform_(self.W.data, gain=1.414)
        self.a = nn.Parameter(torch.zeros(size=(2*out_features, 1)))
        nn.init.xavier_uniform_(self.a.data, gain=1.414)

        self.leakyrelu = nn.LeakyReLU(self.alpha)

    def forward(self, input, adj):
        h = torch.mm(input, self.W)
        N = h.size()[0]

        a_input = torch.cat([h.repeat(1, N).view(N * N, -1), h.repeat(N, 1)], dim=1).view(N, -1, 2 * self.out_features)
        e = self.leakyrelu(torch.matmul(a_input, self.a).squeeze(2))

        zero_vec = -9e15*torch.ones_like(e)
        attention = torch.where(adj > 0, e, zero_vec)
        attention = F.softmax(attention, dim=1)
        attention = F.dropout(attention, self.dropout, training=self.training)
        h_prime = torch.matmul(attention, h)

        if self.concat:
            return F.elu(h_prime), attention
        else:
            return h_prime, attention

    def __repr__(self):
        return self.__class__.__name__ + ' (' + str(self.in_features) + ' -> ' + str(self.out_features) + ')'