Litcius/Paper detail

Fast deep autoencoder for federated learning

David Novoa-Paradela, Óscar Fontenla-Romero, Bertha Guijarro‐Berdiñas

2023Pattern Recognition29 citationsDOIOpen Access PDF

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.

Topics & Concepts

AutoencoderComputer scienceDeep learningArtificial intelligenceEnhanced Data Rates for GSM EvolutionTrainArtificial neural networkDeep belief networkDeep neural networksMachine learningEdge deviceTraining (meteorology)Cloud computingOperating systemMeteorologyGeographyCartographyPhysicsAnomaly Detection Techniques and ApplicationsNetwork Security and Intrusion DetectionPrivacy-Preserving Technologies in Data