Federated Learning and Analytics at Google and Beyond

Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. Similarly, federated analytics (FA) allows data scientists to generate analytical insight from the combined information in distributed datasets without requiring data centralization. FL and FA embody the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. In this talk, I will discuss: (1) how FL and FA differ from more traditional distributed machine learning paradigms, focusing on the main defining characteristics and challenges of the federated setting; and (2) a new federated analytics algorithm for discovering frequent items (heavy hitters) with differential privacy.