Skip to main content

Advertisement

Table 5 Classification accuracies in percent and standard deviations (Number of iterations for HGK-WL and HGK-SP: 20 (100 for SYNTHIE), OOM— Out of Memory

From: A survey on graph kernels

KernelDatasetAverage
 ENZYMESFRANKENSTEINPROTEINSSyntheticNewSynthie 
SP+RBF71.0 ±0.872.8 ±0.276.6 ±0.596.2 ±0.452.8 ±1.873.9
HGK-SP71.3 ±0.970.1 ±0.377.5 ±0.496.5 ±0.694.3 ±0.581.9
HGK-WL67.6 ±1.073.6 ±0.476.7 ±0.498.8 ±0.396.8 ±0.582.7
GH68.8 ±1.068.5 ±0.372.3 ±0.385.1 ±1.073.2 ±0.873.6
GI71.7 ±0.876.3 ±0.376.9 ±0.583.1 ±1.195.8 ±0.580.8
P2K69.2 ±0.4OOM73.5 ±0.591.7 ±0.950.2 ±1.971.2
  1. The highest accuracy value is highlighted in bold for each dataset