# What is Federated Learning? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Model Training  
> **Canonical Citation:** [https://spidits.com/ai-glossary/federated-learning](https://spidits.com/ai-glossary/federated-learning)

## Definition
Federated Learning is a decentralized training technique that trains machine learning models across multiple remote edge devices holding local data samples, without exchanging the data itself.

## Architectural Mechanics & Deep Dive
Federated learning is a distributed machine learning paradigm that trains models across decentralized edge devices or servers holding local data samples, without exchanging the raw data itself. Devices download the global model, train on local data, and upload only the model weight updates to a central server where they are aggregated. This ensures user data privacy and security.

## Industry Applications & Real-World Use Cases
Privacy-first medical diagnostics, smartphone autocomplete tuning, and local data aggregation.

## Frequently Asked Questions

### How does federated learning maintain privacy?
Devices train local model updates on private local data, and only send model weights/gradients to a central server where updates are averaged.

### What is Federated Averaging?
The mathematical algorithm used by the central server to combine the model updates sent by edge nodes to update the global model.

## Related Terminology
- [supervised-learning](https://spidits.com/ai-glossary/supervised-learning)
- [edge-ai](https://spidits.com/ai-glossary/edge-ai)
- [deep-learning](https://spidits.com/ai-glossary/deep-learning)

---
*From the SPIDITS AI Knowledge Base (300+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*