federated-learning
4 free lessons tagged federated-learning across AI. Each one is a short sequence of focused steps with narration and a five-question quiz at the end — take them in any order, no signup required.
Privacy Attacks, Real Guarantees, and Open Models
What model updates actually leak, the two mechanisms that turn data minimisation into a quantified guarantee, poisoning by malicious clients, and what the Apertus project shows about openness at the other end of the spectrum.
Removing the Server: Gossip and Decentralized SGD
What happens when nobody coordinates: averaging by talking only to neighbours, why the graph's spectral gap sets the convergence rate, and how compressing messages by orders of magnitude still converges.
Client Drift: The Heterogeneity Problem
Why local training on non-identical data pulls clients apart, how averaging their updates produces a model that suits nobody, and the control-variate fix that corrects the drift.
Training on Data You Are Not Allowed to See
The federated setting: why hospitals, phones, and banks cannot pool their data, what changes when the training loop crosses a network, and the FedAvg algorithm that made the idea practical.