Welcome to FedPredict

The first-ever plugin for Federated Learning!

FedPredict is a Federated Learning (FL) plugin designed to enhance existing FL solutions without requiring additional training or computational overhead. It enables personalization in standard algorithms such as FedAvg and FedYogi, boosting performance in scenarios with non-IID data.

As a modular component, FedPredict operates exclusively during the prediction phase of FL and does not require any modifications to the training process.

This project has been developed through a collaboration between the WISEMAP Lab (UFMG), H.IAAC Lab (UNICAMP), and NESPED Lab (UFV).

News

Citations:

August 25, 2025 - Data Shift Under Delayed Labeling in Multi-Model Federated Learning, Cláudio G. S. Capanema; Fabrício A. Silva; Leandro A. Villas; Antonio A. F. Loureiro.

May 6, 2025 - ClusterPredict: Enhancing Federated Clustering by Combining Global and Local Parameters, Mingliang Ni and Chaochao Sun.

March 1, 2024 - Adaptive client selection with personalization for communication efficient Federated Learning, Allan M. de Souza, Filipe Maciel, Joahannes B.D. da Costa, Luiz F. Bittencourt, Eduardo Cerqueira, Antonio A.F. Loureiro, and Leandro A. Villas.