-
Notifications
You must be signed in to change notification settings - Fork 7
/
script.py
167 lines (130 loc) · 6.15 KB
/
script.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
from DatasetLoader import DatasetLoader
from MethodWLNodeColoring import MethodWLNodeColoring
from MethodHopDistance import MethodHopDistance
from MethodBertComp import GraphBertConfig
from MethodGraphBert import MethodGraphBert
from MethodGraphBatching import MethodGraphBatching
from MethodGraphBertNodeConstruct import MethodGraphBertNodeConstruct
from MethodGraphBertNodeClassification import MethodGraphBertNodeClassification
from ResultSaving import ResultSaving
from Settings import Settings
from EvaluateAcc import EvaluateAcc
import numpy as np
import torch
#---- 'cora' , 'citeseer', 'pubmed' ----
dataset_name = 'cora'
np.random.seed(1)
torch.manual_seed(1)
#---- cora-small is for debuging only ----
if dataset_name == 'cora':
nclass = 7
nfeature = 1433
ngraph = 2708
#---- Step 1: WL based graph coloring ----
if 0:
print('************ Start ************')
print('WL, dataset: ' + dataset_name)
# ---- objection initialization setction ---------------
data_obj = DatasetLoader()
data_obj.dataset_source_folder_path = './data/' + dataset_name + '/'
data_obj.dataset_name = dataset_name
method_obj = MethodWLNodeColoring()
result_obj = ResultSaving()
result_obj.result_destination_folder_path = './result/WL/'
result_obj.result_destination_file_name = dataset_name
setting_obj = Settings()
evaluate_obj = None
# ------------------------------------------------------
# ---- running section ---------------------------------
setting_obj.prepare(data_obj, method_obj, result_obj, evaluate_obj)
setting_obj.load_run_save_evaluate()
# ------------------------------------------------------
print('************ Finish ************')
#------------------------------------
#---- Step 2: intimacy calculation and subgraph batching ----
if 0:
for k in [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 15, 20, 25, 30, 35, 40, 45, 50]:
print('************ Start ************')
print('Subgraph Batching, dataset: ' + dataset_name + ', k: ' + str(k))
# ---- objection initialization setction ---------------
data_obj = DatasetLoader()
data_obj.dataset_source_folder_path = './data/' + dataset_name + '/'
data_obj.dataset_name = dataset_name
data_obj.compute_s = True
method_obj = MethodGraphBatching()
method_obj.k = k
result_obj = ResultSaving()
result_obj.result_destination_folder_path = './result/Batch/'
result_obj.result_destination_file_name = dataset_name + '_' + str(k)
setting_obj = Settings()
evaluate_obj = None
# ------------------------------------------------------
# ---- running section ---------------------------------
setting_obj.prepare(data_obj, method_obj, result_obj, evaluate_obj)
setting_obj.load_run_save_evaluate()
# ------------------------------------------------------
print('************ Finish ************')
#------------------------------------
#---- Step 3: Shortest path: hop distance among nodes ----
if 0:
for k in [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 15, 20, 25, 30, 35, 40, 45, 50]:
print('************ Start ************')
print('HopDistance, dataset: ' + dataset_name + ', k: ' + str(k))
# ---- objection initialization setction ---------------
data_obj = DatasetLoader()
data_obj.dataset_source_folder_path = './data/' + dataset_name + '/'
data_obj.dataset_name = dataset_name
method_obj = MethodHopDistance()
method_obj.k = k
method_obj.dataset_name = dataset_name
result_obj = ResultSaving()
result_obj.result_destination_folder_path = './result/Hop/'
result_obj.result_destination_file_name = 'hop_' + dataset_name + '_' + str(k)
setting_obj = Settings()
evaluate_obj = None
# ------------------------------------------------------
# ---- running section ---------------------------------
setting_obj.prepare(data_obj, method_obj, result_obj, evaluate_obj)
setting_obj.load_run_save_evaluate()
# ------------------------------------------------------
print('************ Finish ************')
#------------------------------------
#---- Step 4: Graph Bert Node Classification (Cora) ----
if 1:
#---- hyper-parameters ----
k = 7
x_size = nfeature
hidden_size = intermediate_size = 32
num_attention_heads = 2
num_hidden_layers = 2
y_size = nclass
graph_size = ngraph
residual_type = 'graph_raw'
#---- do an early stop when necessary ----
max_epoch = 500
# --------------------------
print('************ Start ************')
print('GrapBert, dataset: ' + dataset_name + ', residual: ' + residual_type + ', k: ' + str(k) + ', hidden dimension: ' + str(hidden_size) +', hidden layer: ' + str(num_hidden_layers) + ', attention head: ' + str(num_attention_heads))
# ---- objection initialization setction ---------------
data_obj = DatasetLoader()
data_obj.dataset_source_folder_path = './data/' + dataset_name + '/'
data_obj.dataset_name = dataset_name
data_obj.k = k
data_obj.load_all_tag = True
bert_config = GraphBertConfig(residual_type = residual_type, k=k, x_size=nfeature, y_size=y_size, hidden_size=hidden_size, intermediate_size=intermediate_size, num_attention_heads=num_attention_heads, num_hidden_layers=num_hidden_layers)
method_obj = MethodGraphBertNodeClassification(bert_config)
#---- set to false to run faster ----
method_obj.spy_tag = True
method_obj.max_epoch = max_epoch
result_obj = ResultSaving()
result_obj.result_destination_folder_path = './result/GraphBert/'
result_obj.result_destination_file_name = dataset_name + '_' + str(num_hidden_layers) + '_' + str(k)
setting_obj = Settings()
evaluate_obj = None
# ------------------------------------------------------
# ---- running section ---------------------------------
setting_obj.prepare(data_obj, method_obj, result_obj, evaluate_obj)
setting_obj.load_run_save_evaluate()
# ------------------------------------------------------
print('************ Finish ************')
#------------------------------------