Português
Ciência-IUL
Publications
Publication Detailed Description
Proceedings of the 31th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2023)
Year (definitive publication)
2023
Language
English
Country
Belgium
More Information
Web of Science®
This publication is not indexed in Web of Science®
Scopus
This publication is not indexed in Scopus
Google Scholar
Abstract
Weightless Neural Networks (WNN) are good candidates for Federated Learning scenarios due to their robustness and computational lightness. In this work, we show that it is possible to aggregate the knowledge of multiple WNNs using more compact data structures, such as Bloom Filters, to reduce the amount of data transferred between devices. Finally, we explore variations of Bloom Filters and found that a particular data-structure, the Count-Min Sketch (CMS), is a good candidate for aggregation. Costing at most 3% of accuracy, CMS can be up to 3x smaller
when compared to previous approaches, specially for large datasets.
Acknowledgements
--
Keywords
Fields of Science and Technology Classification
- Computer and Information Sciences - Natural Sciences
Funding Records
| Funding Reference | Funding Entity |
|---|---|
| UIDP/04466/2020 | Fundação para a Ciência e a Tecnologia |
| 2013/08293-7 | Fapesp |
| 314645/2020-9 | CNPq |
| DSAIPA/AI/0122/2020 | Fundação para a Ciência e a Tecnologia |
| UIDB/04466/2020 | Fundação para a Ciência e a Tecnologia |
| 404087/2021-3 | CNPq |
Related Projects
This publication is an output of the following project(s):
Contributions to the Sustainable Development Goals of the United Nations
With the objective to increase the research activity directed towards the achievement of the United Nations 2030 Sustainable Development Goals, the possibility of associating scientific publications with the Sustainable Development Goals is now available in Ciência-IUL. These are the Sustainable Development Goals identified by the author(s) for this publication. For more detailed information on the Sustainable Development Goals, click here.
