Genetic Programming in Federated Aggregation: A Comparison of FedGP with State of the Art Methods

Created by W.Langdon from gp-bibliography.bib Revision:1.9184

@InProceedings{Pacioni:2025:ICAART,

• author = "Elia Pacioni and Celien Muller and Francisco {Fernandez de Vega} and Davide Calvaresi",
• title = "Genetic Programming in Federated Aggregation: A Comparison of {FedGP} with State of the Art Methods",
• booktitle = "Agents and Artificial Intelligence (ICAART 2025)",
• year = "2025",
• editor = "H. Jaap {van den Herik} and Ana Paula Rocha and Luc Steels",
• volume = "16518",
• series = "Lecture Notes in Computer Science",
• pages = "542--567",
• address = "Porto, Portugal",
• month = feb # " 23-25",
• publisher = "Springer Nature Switzerland",
• note = "Revised Selected Papers, Part III",
• keywords = "genetic algorithms, genetic programming, FedGP, Federated Learning, Multi-Agents System, Models Aggregation, FedAVG, FedPROX, FedNOVA, image collections, PathMNIST, PneumoniaMNIST",
• isbn13 = "978-3-032-25035-3",
• URL = "https://publications.hevs.ch/index.php/publications/show/3244",
• URL = "https://link.springer.com/chapter/10.1007/978-3-032-25035-3_26#citeas",
• DOI = "10.1007/978-3-032-25035-3_26",
• size = "28 pages",
• abstract = "The efficacy of a Federated Learning system is tightly coupled to its model-aggregation strategy. Such a dependency becomes critical when client data are non-IID. To address this challenge, we undertake a comprehensive empirical assessment of FedGP, a genetic programming-based aggregation framework (previously proposed for heterogeneous settings) vs state-of-the-art FL aggregators for non-IID data.",

}

Genetic Programming entries for Elia Pacioni Celien Muller Francisco Fernandez de Vega Davide Calvaresi

Citations