Skip to main content

Table 4 A comparison of the three proposed techniques across different dimensions

From: MINDWALC: mining interpretable, discriminative walks for classification of nodes in a knowledge graph

 

Decision Tree

Random Forest

Feature Transform

Runtime

+

+

++

Interpretability

+++

+

++∗

Predictive performance

+

++

+++

  1. ∗ the feature transform approach is only interpretable if the model where the features are fed to is interpretable