# Federated Learning

> One model learns on many phones. Only the changes travel. The data stays put.

**Field:** Artificial Intelligence  
**Category:** Machine Learning  
**Also known as:** Federated Machine Learning, Collaborative Learning (On-Device)

## Think of it like

It is like a class where each child does homework at home. Only the answers go to school, not the books.

## Definition

Federated learning trains one model across many devices without collecting their data. Each phone or hospital trains a copy of the model on its own data. It sends back only the changes to the model, not the data itself. A server mixes all the changes into one better model. Then it sends that model back out, and the loop repeats. The raw data never leaves home.

## Example

Google tested it in 2017 on Gboard, its phone keyboard. Phones learned better word guesses from typing, and the typing stayed on each phone.

## Why it matters

Some data is too private or too large to move. This lets a model learn from it anyway.

## Common mistake

Thinking it makes the data fully private. Clever attacks can still learn things from the updates, so extra guards are added.

## Three principles

- **Train at home.** Each device trains on its own data.
- **Send changes only.** Updates travel, data stays.
- **Mix and repeat.** A server blends them each round.

## Related terms

- [Supervised Learning](https://learn.benibix.com/term/ai/supervised-learning)
- [Training Data](https://learn.benibix.com/term/ai/training-data)
- [Model Parameter](https://learn.benibix.com/term/ai/model-parameter)
- [Local AI Model](https://learn.benibix.com/term/ai/local-ai-model)

## Taught in

- [RL and Transfer Learning](https://learn.benibix.com/learn/ai-machine-learning/rl-and-transfer-learning): Machine Learning, 7/18

![A server at the top holds the shared model. Three phones below each train on their own data, which stays inside a locked box on the phone. Arrows carry model updates up to the server and the blended model back down.](https://learn.benibix.com/diagrams/ai3-federated.svg)

---

Source: https://learn.benibix.com/term/ai/federated-learning
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-17
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
