top of page
icons8-twitterx-100.png
λογότυπο linkedin
λογότυπο facebook
icons8-youtube-100.png

Federated Learning Aggregation based on Weight Distribution Analysis

Oct 4, 2023

Enhancing Federated Learning: Leveraging Weight Distribution Analysis for Superior Aggregation

Federated learning has recently been proposed as a solution to the problem of using private or sensitive data for training a central deep model, without exchanging the local data. In federated learning, local models are trained on the client side using the available data, while a server is responsible for aggregating the weights of these models into a global model. However, the traditional weight averaging approach does not take into consideration the importance of the different weights for the performance of a model. To this end, this work proposes a novel federated learning weight aggregation method that estimates the statistical distance of each client's parameters from the Gaussianity, and weighs the contribution of each client to the global model accordingly so that the most significant information is retained and enhanced. To create an accurate global model, a complex weighted averaging of the parameters of clients' models at the layer level is performed, considering as low quality the parameters following the Gaussian distribution. The proposed method can be employed to both convolutional and linear layers and it is based on the notion that parameters following a Gaussian distribution do not significantly affect the output of a model. Experiments with different network architectures and a comparison with a plethora of state-of-the-art approaches on three well-known image classification datasets demonstrate the superiority of the proposed method for federated learning weight aggregation.


Read the full publication: https://www.researchgate.net/publication/374440973_Federated_Learning_Aggregation_based_on_Weight_Distribution_Analysis




Εγγραφείτε στο ενημερωτικό μας δελτίο

Ευχαριστούμε για την υποβολή!

Λογότυπο iPROLEPSIS

Το έργο iPROLEPSIS λαμβάνει χρηματοδότηση από την Ευρωπαϊκή Ένωση βάσει της Συμφωνίας Επιχορήγησης με Αρ.101095697.

EN-Funded by the EU-PANTONE.png

Χρηματοδοτείται από την Ευρωπαϊκή Ένωση. Ωστόσο, οι απόψεις και οι απόψεις που εκφράζονται είναι αυτές του συγγραφέα ή των συγγραφέων και δεν αντικατοπτρίζουν απαραίτητα εκείνες της Ευρωπαϊκής Ένωσης ή του Ευρωπαϊκού Οργανισμού Υγείας και Ψηφιακής Εκτελεστικής Υπηρεσίας. Ούτε η Ευρωπαϊκή Ένωση ούτε ο Ευρωπαϊκός Εκτελεστικός Οργανισμός Υγείας και Ψηφιακής Υπηρεσίας μπορούν να θεωρηθούν υπεύθυνοι για αυτά.

© 2025 by iPROLEPSIS Consortium

bottom of page