Federated User Clustering for non-IID Federated Learning

de Sousa Pacheco, Lucas; Rosário, Denis; Cerqueira, Eduardo; Braun, Torsten (September 2021). Federated User Clustering for non-IID Federated Learning. In: International Conference on Networked Systems 2021 (NetSys 2021). Lübeck, Germany. 13-16 September 2021.

Full text not available from this repository. (Request a copy)

Federated Learning (FL) is one of the leading learning paradigms for enabling a more significant presence of intelligent applications in networking considering highly distributed environments while preserving user privacy. However, FL has the significant shortcoming of requiring user data to be Independent Identically Distributed (IID) to make reliable predictions for a given group of users. We present a Neural Network-based Federated Clustering mechanism capable of clustering the local models trained by users of the network with no access to their raw data. We also present an alternative to the FedAvg aggregation algorithm used in traditional FL, which significantly increases the aggregated models’ reliability in Mean Square Error by creating several training models over IID users.

Item Type:

Conference or Workshop Item (Paper)

Division/Institute:

08 Faculty of Science > Institute of Computer Science (INF)
08 Faculty of Science > Institute of Computer Science (INF) > Communication and Distributed Systems (CDS)

UniBE Contributor:

de Sousa Pacheco, Lucas and Braun, Torsten

Subjects:

000 Computer science, knowledge & systems
500 Science > 510 Mathematics
500 Science
600 Technology

Language:

English

Submitter:

Dimitrios Xenakis

Date Deposited:

22 Apr 2021 18:11

Last Modified:

17 Sep 2021 12:42

URI:

https://boris.unibe.ch/id/eprint/154992

Actions (login required)

Edit item Edit item
Provide Feedback