graphstorm.eval

GraphStorm provides built-in evaluation methods for different Graph Machine Learning (GML) tasks.

If users want to implement customized evaluators or evaluation methods, a best practice is to extend base evaluators, i.e., the GSgnnInstanceEvaluator class for node or edge prediction tasks, and GSgnnLPEvaluator for link prediction tasks, and then implement the abstract methods.

Base Evaluators

`GSgnnInstanceEvaluator`	Template class for user defined evaluator.
`GSgnnLPEvaluator`	Template class for user defined evaluator.

Evaluators

`GSgnnLPEvaluator`	Template class for user defined evaluator.
`GSgnnMrrLPEvaluator`	The class for link prediction evaluation using Mrr metric.
`GSgnnPerEtypeMrrLPEvaluator`	The class for link prediction evaluation using Mrr metric and
`GSgnnAccEvaluator`	The class for user defined evaluator.
`GSgnnRegressionEvaluator`	The class for user defined evaluator.