-
Notifications
You must be signed in to change notification settings - Fork 257
/
node_classification.py
170 lines (138 loc) · 6.92 KB
/
node_classification.py
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
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
import os.path as osp
import torch
import torch.nn.functional as F
from torch_geometric.data import (InMemoryDataset, download_url)
from torch_geometric.nn import GATConv, Sequential
from torch_geometric.transforms import NormalizeFeatures
from torch_geometric.io import read_planetoid_data
from torch.nn import Linear, ReLU
class PlanetoidPubMed(InMemoryDataset):
r"""The citation network datasets "PubMed" from the
`"Revisiting Semi-Supervised Learning with Graph Embeddings"
<https://arxiv.org/abs/1603.08861>`_ paper.
Nodes represent documents and edges represent citation links.
Training, validation and test splits are given by binary masks.
Args:
root (string): Root directory where the dataset should be saved.
split (string): The type of dataset split
(:obj:`"public"`, :obj:`"full"`, :obj:`"random"`).
If set to :obj:`"public"`, the split will be the public fixed split
from the
`"Revisiting Semi-Supervised Learning with Graph Embeddings"
<https://arxiv.org/abs/1603.08861>`_ paper.
If set to :obj:`"full"`, all nodes except those in the validation
and test sets will be used for training (as in the
`"FastGCN: Fast Learning with Graph Convolutional Networks via
Importance Sampling" <https://arxiv.org/abs/1801.10247>`_ paper).
If set to :obj:`"random"`, train, validation, and test sets will be
randomly generated, according to :obj:`num_train_per_class`,
:obj:`num_val` and :obj:`num_test`. (default: :obj:`"public"`)
num_train_per_class (int, optional): The number of training samples
per class in case of :obj:`"random"` split. (default: :obj:`20`)
num_val (int, optional): The number of validation samples in case of
:obj:`"random"` split. (default: :obj:`500`)
num_test (int, optional): The number of test samples in case of
:obj:`"random"` split. (default: :obj:`1000`)
transform (callable, optional): A function/transform that takes in an
:obj:`torch_geometric.data.Data` object and returns a transformed
version. The data object will be transformed before every access.
(default: :obj:`None`)
pre_transform (callable, optional): A function/transform that takes in
an :obj:`torch_geometric.data.Data` object and returns a
transformed version. The data object will be transformed before
being saved to disk. (default: :obj:`None`)
"""
url = 'https://github.com/kimiyoung/planetoid/raw/master/data'
def __init__(self, root, split="public", num_train_per_class=20,
num_val=500, num_test=1000, transform=None,
pre_transform=None):
super(PlanetoidPubMed, self).__init__(root, transform, pre_transform)
self.data, self.slices = torch.load(self.processed_paths[0])
self.split = split
assert self.split in ['public', 'full', 'random']
if split == 'full':
data = self.get(0)
data.train_mask.fill_(True)
data.train_mask[data.val_mask | data.test_mask] = False
self.data, self.slices = self.collate([data])
elif split == 'random':
data = self.get(0)
data.train_mask.fill_(False)
for c in range(self.num_classes):
idx = (data.y == c).nonzero(as_tuple=False).view(-1)
idx = idx[torch.randperm(idx.size(0))[:num_train_per_class]]
data.train_mask[idx] = True
remaining = (~data.train_mask).nonzero(as_tuple=False).view(-1)
remaining = remaining[torch.randperm(remaining.size(0))]
data.val_mask.fill_(False)
data.val_mask[remaining[:num_val]] = True
data.test_mask.fill_(False)
data.test_mask[remaining[num_val:num_val + num_test]] = True
self.data, self.slices = self.collate([data])
@property
def raw_dir(self):
return osp.join(self.root, 'raw')
@property
def processed_dir(self):
return osp.join(self.root, 'processed')
@property
def raw_file_names(self):
names = ['x', 'tx', 'allx', 'y', 'ty', 'ally', 'graph', 'test.index']
return ['ind.pubmed.{}'.format(name) for name in names]
@property
def processed_file_names(self):
return 'data.pt'
def download(self):
for name in self.raw_file_names:
download_url('{}/{}'.format(self.url, name), self.raw_dir)
def process(self):
data = read_planetoid_data(self.raw_dir, 'pubmed')
data = data if self.pre_transform is None else self.pre_transform(data)
torch.save(self.collate([data]), self.processed_paths[0])
def __repr__(self):
return '{}()'.format(self.name)
dataset = PlanetoidPubMed(root='data/PlanetoidPubMed/', transform=NormalizeFeatures())
print('dataset.num_features:', dataset.num_features)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
data = dataset[0].to(device)
def train():
model.train()
optimizer.zero_grad() # Clear gradients.
out = model(data.x, data.edge_index) # Perform a single forward pass.
# Compute the loss solely based on the training nodes.
loss = criterion(out[data.train_mask], data.y[data.train_mask])
loss.backward() # Derive gradients.
optimizer.step() # Update parameters based on gradients.
return loss
def test():
model.eval()
out = model(data.x, data.edge_index)
pred = out.argmax(dim=1) # Use the class with highest probability.
test_correct = pred[data.test_mask] == data.y[data.test_mask] # Check against ground-truth labels.
test_acc = int(test_correct.sum()) / int(data.test_mask.sum()) # Derive ratio of correct predictions.
return test_acc
class GAT(torch.nn.Module):
def __init__(self, num_features, hidden_channels_list, num_classes):
super(GAT, self).__init__()
torch.manual_seed(12345)
hns = [num_features] + hidden_channels_list
conv_list = []
for idx in range(len(hidden_channels_list)):
conv_list.append((GATConv(hns[idx], hns[idx+1]), 'x, edge_index -> x'))
conv_list.append(ReLU(inplace=True),)
self.convseq = Sequential('x, edge_index', conv_list)
self.linear = Linear(hidden_channels_list[-1], num_classes)
def forward(self, x, edge_index):
x = self.convseq(x, edge_index)
x = F.dropout(x, p=0.5, training=self.training)
x = self.linear(x)
return x
model = GAT(num_features=dataset.num_features, hidden_channels_list=[200, 100], num_classes=dataset.num_classes).to(device)
print(model)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)
criterion = torch.nn.CrossEntropyLoss()
for epoch in range(1, 201):
loss = train()
print(f'Epoch: {epoch:03d}, Loss: {loss:.4f}')
test_acc = test()
print(f'Test Accuracy: {test_acc:.4f}')