Evaluation of Advanced Data Structures for Federated Learning Processes: Complexity, Trade-offs, and Design Considerations

Authors

Anthony Njina, Meru University of Science & Technology, Kenya

Stephen Mutua, Meru University of Science & Technology, Kenya

Mary Mwadulo, Meru University of Science & Technology, Kenya

Published in

IST-Africa 2026 Conference Proceedings

ISSN: 2576-8581

ISBN: 978-1-905824-76-2

DOI: https://doi.org/10.67725/IST-Africa.2026.SOMO7899

Publisher

IST-Africa Institute and IIMC International Information Management Corporation Ltd

Published in Ireland

Abstract

Federated Learning (FL) enables collaborative training across distributed devices without centralizing sensitive data, but it faces challenges of heterogeneity, communication overhead, and privacy risks. This study explores how advanced data structures can improve efficiency and security in FL processes. Using simulations with the EMNIST dataset, we evaluate structures including sparse arrays, hash tables, Bloom filters, queues, Merkle trees, and dense tensors. Results highlight key trade-offs: Bloom filters speed up client selection, sparse matrices save memory in local training, hash maps streamline aggregation, and delta encoding reduces redistribution costs. No single structure is universally optimal; each offers unique advantages depending on context. Our findings provide practical guidance for designing scalable and secure FL systems that balance performance, resource use, and privacy.

Keywords

Federated Learning, Advanced Data Structures, Privacy Preservation, Scalability

Cite this paper

A. Njina, S. Mutua and M. Mwadulo (2026) "Evaluation of Advanced Data Structures for Federated Learning Processes: Complexity, Trade-offs, and Design Considerations", IST-Africa 2026 Conference Proceedings, Miriam Cunningham and Paul Cunningham (Eds), IST-Africa Institute and IIMC, 2026, ISSN: 2576-8581, ISBN: 978-1-905824-76-2, https://doi.org/10.67725/IST-Africa.2026.SOMO7899

Access Paper

Click here to access this paper

IST-Africa Community Members can download papers by logging into their existing account.

If you wish to become a member of IST-Africa Community, please register your profile and you will then receive login details which you can use to access the papers.

Access to papers in the IST-Africa 2026 Conference Proceedings is for INDIVIDUAL USE only. Neither the Conference Proceedings (or individual double blind peer reviewed papers) are to be included in any public or institutional repository or processed in the context of any AI tool or large language model without prior written permission from the Publishers.

While the IST-Africa Institute and IIMC retain copyright of the Conference Proceedings, each author retains copyright to their individual paper. No paper or part thereof may be reproduced without the written permission of both the Conference Proceedings Publishers and appropriate author(s).