Federated learning is a machine learning approach that allows multiple devices to collaboratively train a shared model while keeping their data decentralized. In this method, instead of sending all data to a central server for training, the model is sent out to individual devices or nodes, which then compute partial model updates based on their local data. These updates are then aggregated to create a global model without sharing any raw data. Federated learning enables better privacy protection, reduces the need for data centralization, and allows for more efficient training on distributed datasets.
This mind map was published on 29 March 2024 and has been viewed 81 times.