Federated Learning

Full definition

In federated learning, a coordinator broadcasts a model to each participant; each participant trains locally on its private data and sends back only model updates (gradients or weight deltas); the coordinator aggregates the updates into a new global model. Originally developed at Google for keyboard next-word prediction on Android, it is now applied in healthcare consortia, finance fraud detection, and IoT.

Why it matters

Federated learning is one of the few mechanisms that lets multiple organizations co-train AI on their combined data without breaching privacy or regulatory boundaries — a structural realize for healthcare, finance, and cross-border industries. Combined with differential privacy, it raises the bar for what is possible inside strict data-residency regimes.

Example

Five European hospitals use federated learning to co-train a sepsis-prediction model on combined data from 2 million patients — raw records never cross hospital boundaries, satisfying GDPR while delivering accuracy that no individual hospital's data could achieve alone.

Related terms

• Differential Privacy
  Differential privacy is a mathematical framework that bounds how much any single individual's data can influence the output of an analysis or trained model — providing a quantifiable privacy guarantee (epsilon) rather than relying on after-the-fact anonymization.
• Training Data
  Training data is the curated dataset used to teach a machine-learning model — every pattern the model can recognize, every bias it inherits, and every limit to its accuracy ultimately traces back to this data.
• AI Governance
  AI governance is the framework of policies, roles, controls, and processes an organization uses to ensure its AI systems are lawful, safe, fair, accountable, and aligned with business intent — across the full lifecycle from problem framing to retirement.
• Edge AI
  Edge AI is the practice of running AI models on local devices — smartphones, vehicles, sensors, factory equipment, AR/VR headsets — instead of the cloud, in order to deliver lower latency, stronger privacy, and continued operation when offline.
• Machine Learning (ML)
  Machine Learning (ML) is the subfield of AI in which algorithms improve their performance on a task by learning statistical patterns from data, rather than following rules a human wrote by hand.