A machine learning approach where a model is trained across multiple decentralized edge devices or servers holding local data samples, without exchanging them.
Federated Learning lets organizations train AI models collaboratively without centralizing sensitive data. Each participating device or server trains the model on its own local data, and only the resulting model updates, not the raw data, are sent for central aggregation. Keeping raw data local reduces privacy exposure, which makes the approach well suited to healthcare and defense deployments.
See also Large Language Model, Fine-Tuning and Model Inference.