search

choi328328 / FederatedPLP

Apache License 2.0
5 stars 0 forks source link

Federated XGB #3

Open choi328328 opened 1 year ago

choi328328 commented 1 year ago

Until now, XGB seems the most credible tabular model algorithm. Also, histogram-based XGboost is a CPU-trainable model algorithm.

And also, when we validate the model in other CDM databases, XGboost will be the easiest way. I'm not sure that the other PyTorch model is CDM applicable or not

So, I think we should apply Federated XGB to our package

choi328328 commented 1 year ago

The model should works on scikit-learn API and can be converted to OMOP CDM validation package