Distributed Learning
A machine learning approach where training data is distributed across multiple devices or locations, and models are trained collaboratively without sharing raw data.
Definition
Includes federated learning and split-learning: each node trains locally on private data and shares model updates or embeddings with a central server. This preserves data privacy and reduces bandwidth, but requires secure aggregation, drift handling, and governance for update validation to prevent poisoned-update attacks.
Real-World Example
A healthcare consortium trains a disease-prediction model across five hospitals using federated learning. Each hospital trains on its patient records locally, sends encrypted weight updates, and the central server aggregates them—enabling a robust model without exposing any patient data externally.
.svg)
