We're new to Neo4j and currently looking at using it for classifying nodes. Out of the box I see there are a few models as part of the GDS library (namely Logistic Regression and Random Forest) and we were wondering if there's any way to build our own custom classification model and add it to a pipeline?
Adding custom models to exisiting pipelines in GDS is not yet supported. However, it is very easy to use gds python client and integrate GDS (graphy features) into custom ML pipelines built in Python.
Adding custom models to exisiting pipelines in GDS is not yet supported. However, it is very easy to use gds python client and integrate GDS (graphy features) into custom ML pipelines built in Python.
Do you have a specific classifier in mind? At the moment we dont have a mechanism to discover new training methods but only check ours. I certainly like the idea to have a discover mechanism so that people can write their custom classifier in Java.
