5 datasets found

The dataset used in the paper is a benchmark dataset for decentralized learning, consisting of 20 clients with different models and data distributions.

We propose a decentralized online learning algorithm in Hilbert spaces.

We establish a framework of distributed random inverse problems over network graphs with online measurements, and propose a decentralized online learning algorithm.

DeceFL is a decentralized federated learning algorithm that eliminates the need for a central server and maintains convergence property.

The dataset used in the paper is a network of agents with heterogeneous objectives and data.