Novoa-Paradela, DavidFontenla-Romero, ÓscarGuijarro-Berdiñas, Bertha2023-11-272023-11-272023-11D. Novoa-Paradela, Óscar Fontenla-Romero, and B. Guijarro-Berdiñas, "Fast deep autoencoder for federated learning", Pattern Recognition, Vol. 143, Nov. 2023, 109805, doi: https://doi.org/10.1016/j.patcog.2023.109805http://hdl.handle.net/2183/34337Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG[Abstract]: This paper presents a novel, fast and privacy preserving implementation of deep autoencoders. DAEF (Deep AutoEncoder for Federated learning), unlike traditional neural networks, trains a deep autoencoder network in a non-iterative way, which drastically reduces training time. Training can be performed incrementally, in parallel and distributed and, thanks to its mathematical formulation, the information to be exchanged does not endanger the privacy of the training data. The method has been evaluated and compared with other state-of-the-art autoencoders, showing interesting results in terms of accuracy, speed and use of available resources. This makes DAEF a valid method for edge computing and federated learning, in addition to other classic machine learning scenarios.engAtribución 4.0 Internacional (CC BY 4.0)http://creativecommons.org/licenses/by/3.0/es/Anomaly detectionDeep autoencoderEdge computingFederated learningMachine learningjournal articleopen access10.1016/j.patcog.2023.109805