File size: 2,826 Bytes
d38bce3 |
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 |
import seaborn as sns; sns.set()
import matplotlib.pyplot as plt
from tqdm import tqdm
import os
import numpy as np
import scipy.sparse as sp
def degree_dist(clean_adj, perturbed_adj, savename='degree_dist.pdf'):
"""Plot degree distributnio on clean and perturbed graphs.
Parameters
----------
clean_adj: sp.csr_matrix
adjancecy matrix of the clean graph
perturbed_adj: sp.csr_matrix
adjancecy matrix of the perturbed graph
savename: str
filename to be saved
Returns
-------
None
"""
clean_degree = clean_adj.sum(1)
perturbed_degree = perturbed_adj.sum(1)
fig, ax1 = plt.subplots()
sns.distplot(clean_degree, label='Clean Graph', norm_hist=False, ax=ax1)
sns.distplot(perturbed_degree, label='Perturbed Graph', norm_hist=False, ax=ax1)
ax1.grid(False)
plt.legend(prop={'size':18})
plt.ylabel('Density Distribution', fontsize=18)
plt.xlabel('Node degree', fontsize=18)
plt.xticks(fontsize=14)
plt.yticks(fontsize=14)
# plt.title(f'Feature difference of adjacency after {attack}-attack')
if not os.path.exists('figures/'):
os.mkdir('figures')
plt.savefig('figures/%s' % savename, bbox_inches='tight')
plt.show()
def feature_diff(clean_adj, perturbed_adj, features, savename='feature_diff.pdf'):
"""Plot feature difference on clean and perturbed graphs.
Parameters
----------
clean_adj: sp.csr_matrix
adjancecy matrix of the clean graph
perturbed_adj: sp.csr_matrix
adjancecy matrix of the perturbed graph
features: sp.csr_matrix or np.array
node features
savename: str
filename to be saved
Returns
-------
None
"""
fig, ax1 = plt.subplots()
sns.distplot(_get_diff(clean_adj, features), label='Normal Edges', norm_hist=True, ax=ax1)
delta_adj = perturbed_adj - clean_adj
delta_adj[delta_adj < 0] = 0
sns.distplot(_get_diff(delta_adj, features), label='Adversarial Edges', norm_hist=True, ax=ax1)
ax1.grid(False)
plt.legend(prop={'size':18})
plt.ylabel('Density Distribution', fontsize=18)
plt.xlabel('Feature Difference Between Connected Nodes', fontsize=18)
plt.xticks(fontsize=14)
plt.yticks(fontsize=14)
if not os.path.exists('figures/'):
os.mkdir('figures')
plt.savefig('figures/%s' % savename, bbox_inches='tight')
plt.show()
def _get_diff(adj, features):
isSparse = sp.issparse(features)
edges = np.array(adj.nonzero()).T
row_degree = adj.sum(0).tolist()[0]
diff = []
for edge in tqdm(edges):
n1 = edge[0]
n2 = edge[1]
if n1 > n2:
continue
d = np.sum((features[n1]/np.sqrt(row_degree[n1]) - features[n2]/np.sqrt(row_degree[n2])).power(2))
diff.append(d)
return diff
|