Evaluation-Framework

It is an evaluation framework for evaluating and comparing graph embedding techniques

Regression

Datasets used as gold standard

Dataset Semantic of classes Size Source
Cities Living style 212 Mercer
AAUP Salary of professors 960 JSE
Forbes Agency income 1,585 Forbes
Albums Album popularity 1,600 Metacritic
Movies Movie popularity 2,000 Metacritic

Model and its configuration

Model Configuration
Linear Regression -
M5Rules -
k-NN k=3

Missing entities are simply ignored.

The results are calculated using stratified 10-fold cross-validation.

Output of the evaluation

Metric Range Optimum
Root Mean Squared Error (RMSE) [0,1] Lowest