MORAIDICTIONNAIRE IA
Infrastructure

Federated Learning

Train an AI model without ever centralizing the data — it stays where it lives.

Imagine several hospitals wanting to jointly train a single diagnostic model, yet never exchanging a single patient record. That is exactly the promise of federated learning: instead of bringing the data to the model, you bring the model to the data. The model travels; the data stays home.

How it works

The principle relies on a repeated cycle, orchestrated by a central server and dozens, thousands or millions of clients (phones, hospitals, banks):

  1. The server sends the current global model to each client.
  2. Each client trains it locally on its own data.
  3. Clients send back only the weight updates (gradients), never the raw data.
  4. The server aggregates these updates into a new global version.

The canonical algorithm, FedAvg, computes an average weighted by each client's number of examples $n_k$:

$$ w_{t+1} = \sum_{k=1}^{K} \frac{n_k}{n} \, w_t^k $$

Centralized or federated?

Criterion Centralized learning Federated learning
Data location Single server Stays on the client
Privacy Low High
Network cost Massive data transfer Model transfer only
Difficulty Simple Non-IID data, heterogeneous clients

Where you meet it

Federated learning moves the training, not the data — a pillar for reconciling collective intelligence with privacy.

Explore the full AI dictionary →