An introduction to marketing strategy

Benefits

Federated learning is a machine learning (ML) technique that allows multiple parties to train a model without sharing data

How it works

Each party trains a local model on their own data, and then only sends the local model to an aggregator. The aggregator uses these local models to improve the global model, which benefits all parties

Improvement

Google uses federated learning in G board to improve performance without sending personal data to its central servers. This includes features like next-word prediction, emoji suggestion, and autocorrect