Table 4 Comparison of prediction accuracy under the metric of root mean squared error when only the weight information is missing for some links.

From: Weight prediction in complex networks based on neighbor set

Network\Index

Linear-correlation

Ours

CN

WCN

rWCN

AA

WAA

rWAA

RA

WRA

rWRA

Celegans

0.207

0.206

0.206

0.206

0.204

0.204

0.204

0.203

0.203

0.203

Everglades

0.172

0.171

0.154

0.171

0.164

0.15

0.171

0.164

0.156

0.162

USAir1

0.00587

0.00482

0.00531

0.00587

0.00571

0.00536

0.00586

0.00573

0.00555

0.00593

USAir2

0.136

0.136

0.136

0.136

0.136

0.136

0.138

0.138

0.137

0.134

Advogato

0.107

0.106

0.105

0.106

0.105

0.105

0.106

0.105

0.104

0.108

Geom

0.173

0.166

0.158

0.173

0.166

0.153

0.173

0.171

0.151

0.185

  1. The validation set always contains 10% of the links from the example network. Each accuracy value is an average over 100 independent random divisions of the links into a training set and a validation set. In each network, the best performance is emphasized in bold.
Back to article page