Skip to main content

Federated Learning


Federated Learning is a decentralized machine learning approach that enables the training of models across multiple devices or servers while keeping the data localized, without the need to centralize the data in one location.

The main idea behind federated learning is to improve data privacy and security, as well as reduce communication overhead and dependence on a centralized data storage system.

Here is a video to help you understand the concept better:


In traditional machine learning, a model is trained on a centralized server using a large dataset that is collected from various sources. However, this approach raises privacy concerns since the data may contain sensitive information, and centralizing the data could lead to potential data breaches or misuse.

Federated Learning addresses these privacy concerns by allowing devices to train models locally on their data without sharing the raw data with a central server.