N1H111SM's Miniverse

GCN - Code Explanation

字数统计: 900阅读时长: 5 min
2020/05/16 Share

Materials

Graph Convolution Layer

Sometimes you will want to specify models that are more complex than a sequence of existing Modules; for these cases you can define your own Modules by subclassing nn.Module and defining a forward which receives input Tensors and produces output Tensors using other modules or other autograd operations on Tensors.

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
import math
import torch

from torch.nn.parameter import Parameter
from torch.nn.modules.module import Module


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

def __init__(self, in_features, out_features, bias=True):
super(GraphConvolution, self).__init__()
self.in_features = in_features
self.out_features = out_features
self.weight = Parameter(torch.FloatTensor(in_features, out_features))
if bias:
self.bias = Parameter(torch.FloatTensor(out_features))
else:
self.register_parameter('bias', None)
self.reset_parameters()

def reset_parameters(self):
stdv = 1. / math.sqrt(self.weight.size(1))
self.weight.data.uniform_(-stdv, stdv)
if self.bias is not None:
self.bias.data.uniform_(-stdv, stdv)

def forward(self, input, adj):
support = torch.mm(input, self.weight)
output = torch.spmm(adj, support)
if self.bias is not None:
return output + self.bias
else:
return output

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

reset_parameters(): 随机eeee化策略的standard deviation由weight维度的长度决定。

forward(): 注意GCN原文中关于Adjacency Matrix renormalization trick:

所以我们可以推定该函数中的参数adj不是原本的邻接矩阵,而是经过转换的邻接矩阵。而同时Graph Convolution公式:

support = torch.mm(input, self.weight) 表示了$X\Theta$矩阵乘法,其中torch.mm表示的是matrix multiplication. 而output = torch.spmm(adj, support) 表示的是最后的结果,因为adj是一个sparse matrix,所以需要采用torch.spmm,表示的是sparse matrix multiplication.

GCN

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
import torch.nn as nn
import torch.nn.functional as F
from pygcn.layers import GraphConvolution


class GCN(nn.Module):
def __init__(self, nfeat, nhid, nclass, dropout):
super(GCN, self).__init__()

self.gc1 = GraphConvolution(nfeat, nhid)
self.gc2 = GraphConvolution(nhid, nclass)
self.dropout = dropout

def forward(self, x, adj):
x = F.relu(self.gc1(x, adj))
x = F.dropout(x, self.dropout, training=self.training)
x = self.gc2(x, adj)
return F.log_softmax(x, dim=1)

__init__(): 定义了两层convolution layer,最终的output是node-level的类别,因为GCN最初提出时要解决的问题是semi-supervised learning.

Data

Training

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
from __future__ import division
from __future__ import print_function

import time
import argparse
import numpy as np

import torch
import torch.nn.functional as F
import torch.optim as optim

from pygcn.utils import load_data, accuracy
from pygcn.models import GCN

# Training settings
parser = argparse.ArgumentParser()
parser.add_argument('--no-cuda', action='store_true', default=False,
help='Disables CUDA training.')
parser.add_argument('--fastmode', action='store_true', default=False,
help='Validate during training pass.')
parser.add_argument('--seed', type=int, default=42, help='Random seed.')
parser.add_argument('--epochs', type=int, default=200,
help='Number of epochs to train.')
parser.add_argument('--lr', type=float, default=0.01,
help='Initial learning rate.')
parser.add_argument('--weight_decay', type=float, default=5e-4,
help='Weight decay (L2 loss on parameters).')
parser.add_argument('--hidden', type=int, default=16,
help='Number of hidden units.')
parser.add_argument('--dropout', type=float, default=0.5,
help='Dropout rate (1 - keep probability).')

args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()

np.random.seed(args.seed)
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)

# Load data
adj, features, labels, idx_train, idx_val, idx_test = load_data()

# Model and optimizer
model = GCN(nfeat=features.shape[1],
nhid=args.hidden,
nclass=labels.max().item() + 1,
dropout=args.dropout)
optimizer = optim.Adam(model.parameters(),
lr=args.lr, weight_decay=args.weight_decay)

if args.cuda:
model.cuda()
features = features.cuda()
adj = adj.cuda()
labels = labels.cuda()
idx_train = idx_train.cuda()
idx_val = idx_val.cuda()
idx_test = idx_test.cuda()


def train(epoch):
t = time.time()
model.train()
optimizer.zero_grad()
output = model(features, adj)
loss_train = F.nll_loss(output[idx_train], labels[idx_train])
acc_train = accuracy(output[idx_train], labels[idx_train])
loss_train.backward()
optimizer.step()

if not args.fastmode:
# Evaluate validation set performance separately,
# deactivates dropout during validation run.
model.eval()
output = model(features, adj)

loss_val = F.nll_loss(output[idx_val], labels[idx_val])
acc_val = accuracy(output[idx_val], labels[idx_val])
print('Epoch: {:04d}'.format(epoch+1),
'loss_train: {:.4f}'.format(loss_train.item()),
'acc_train: {:.4f}'.format(acc_train.item()),
'loss_val: {:.4f}'.format(loss_val.item()),
'acc_val: {:.4f}'.format(acc_val.item()),
'time: {:.4f}s'.format(time.time() - t))


def test():
model.eval()
output = model(features, adj)
loss_test = F.nll_loss(output[idx_test], labels[idx_test])
acc_test = accuracy(output[idx_test], labels[idx_test])
print("Test set results:",
"loss= {:.4f}".format(loss_test.item()),
"accuracy= {:.4f}".format(acc_test.item()))


# Train model
t_total = time.time()
for epoch in range(args.epochs):
train(epoch)
print("Optimization Finished!")
print("Total time elapsed: {:.4f}s".format(time.time() - t_total))

# Testing
test()
CATALOG
  1. 1. Graph Convolution Layer
  2. 2. GCN
  3. 3. Data
  4. 4. Training