About

FedPredict is an open-source project freely available on Github under the BSD-3 license. The project is led by Cláudio G. S. Capanema and has been developed across the laboratories WISEMAP (UFMG), H.IAAC (UNICAMP), and NESPED-Lab (UFV).

Citing

If FedPredict has been useful to you, please cite our papers.

FedPredict: Combining Global and Local Parameters in the Prediction Step of Federated Learning (original paper):

@INPROCEEDINGS{capanema2023fedpredict,
  author={Capanema, Cláudio G. S. and de Souza, Allan M. and Silva, Fabrício A. and Villas, Leandro A. and Loureiro, Antonio A. F.},
  booktitle={2023 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT)}, 
  title={FedPredict: Combining Global and Local Parameters in the Prediction Step of Federated Learning}, 
  year={2023},
  volume={},
  number={},
  pages={17-24},
  keywords={Federated learning;Computational modeling;Neural networks;Mathematical models;Internet of Things;Distributed computing;Personalized Federated Learning;Neural Networks;Federated Learning Plugin},
  doi={10.1109/DCOSS-IoT58021.2023.00012}}

A Novel Prediction Technique for Federated Learning (extended journal paper):

@ARTICLE{capanema2025@novel,
  author={Capanema, Cláudio G. S. and de Souza, Allan M. and da Costa, Joahannes B. D. and Silva, Fabrício A. and Villas, Leandro A. and Loureiro, Antonio A. F.},
  journal={IEEE Transactions on Emerging Topics in Computing}, 
  title={A Novel Prediction Technique for Federated Learning}, 
  year={2025},
  volume={13},
  number={1},
  pages={5-21},
  keywords={Servers;Costs;Training;Downlink;Adaptation models;Computational modeling;Federated learning;Quantization (signal);Context modeling;Accuracy;Federated learning plugin;neural networks;personalized federated learning},
  doi={10.1109/TETC.2024.3471458}}

A Modular Plugin for Concept Drift in Federated Learning (FedPredict-Dynamic):

@INPROCEEDINGS{capanema2024@modular,
  author={Capanema, Cláudio G. S. and Da Costa, Joahannes B. D. and Silva, Fabrício A. and Villas, Leandro A. and Loureiro, Antonio A. F.},
  booktitle={2024 20th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT)}, 
  title={A Modular Plugin for Concept Drift in Federated Learning}, 
  year={2024},
  volume={},
  number={},
  pages={101-108},
  keywords={Training;Accuracy;Federated learning;Geology;Concept drift;Data models;Internet of Things;Concept Drift;Personalized Federated Learning;Federated Learning Plugin;Neural Networks},
  doi={10.1109/DCOSS-IoT61029.2024.00024}}