Originally published at: https://developer.nvidia.com/blog/federated-xgboost-made-practical-and-productive-with-nvidia-flare/
XGBoost is a highly effective and scalable machine learning algorithm widely employed for regression, classification, and ranking tasks. Building on the principles of gradient boosting, it combines the predictions of multiple weak learners, typically decision trees, to produce a robust overall model. XGBoost excels with large datasets and complex data structures, thanks to its efficient…
1 Like
Being able to run several concurrent experiments are always good for production env setting. If we have a cross-countries with multiple financial institutions working on fraud protection, it would be hard to request different ports open for each job from IT. NVFLARE’s port multiplexing make running concurrent jobs easy. With cross-boarder training, the network interruption tolerance is nice feature, one doesn’t need to restart from beginning.
Its neat to be able switch different experiment tracking system without re-writing the metrics logging code. If user can simply log to the metrics and streamed to the server, now we have overall view of all metrics from MLFlow or W&B. If user changes the mind, they can configuration, then metrics is streamed to the client site. Really cool.