Federated learning

AIGP glossary · Last reviewed: 2026-07-08 · By Victor Humenhuk (AIGP certified)

Federated learning - PET where local systems train a central model on their own datasets, aggregated centrally without exposing individual data.

In the AIGP body of knowledge, Federated learning comes up under Module 6: Governing AI Development · BoK III.B; Module 8: AI Governance Vocabulary.

Federated learning in context

• Master the two PETs - ==differential privacy blurs the data==; ==federated learning moves the training, not the data==. (Wrangling the Data)
• The named techniques and model types that show up as one-line scenario answers - including ==federated learning== (data never leaves the site), transfer learning, fine-tuning, and the discriminative-vs-generative split. (Learning techniques and methods)

Where Federated learning is covered in the AIGP study notes

• Wrangling the Data
• Learning techniques and methods

Related terms

• Data cleansing
• Data labelling
• Anonymisation
• Purpose specification & minimisation
• Differential privacy
• Active learning
• Adaptive learning
• Transfer learning model
• Fine-tuning
• Classification model

Test yourself on Federated learning

Recognising a definition is not the same as applying it in an exam scenario. Work through the free AIGP practice questions, or read the full AIGP study guide - every study note is free.

← Back to the AIGP glossary