Conference paper · 2026 · Open access
FedAR: Adaptive Client Selection Strategy for Heterogeneous Federated Learning
International Conference on Communications, 1–6 · Published 24 May 2026 · DOI 10.1109/icc59461.2026.11588258
In brief
“FedAR: Adaptive Client Selection Strategy for Heterogeneous Federated Learning” is a 2026 conference paper by Vahideh Hayyolalam and Öznur Özkasap, published in International Conference on Communications. OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at International Conference on Communications.
- Citations
- 0
- References
- 8
- Authors
- 2
Abstract
Federated learning (FL) allows multiple participants to collaboratively train a shared model without exposing or exchanging their raw data, yet heterogeneous client resources and non-IID data often slow convergence and hurt fairness. We propose FedAR, an adaptive client selection strategy that formulates selection as a similarity-alignment problem between a Global Environmental Vector and per-client Environmental Vectors. FedAR computes cosine similarity and refines it with (i) a communication-efficiency penalty, (ii) an aging mechanism to prevent over-selection, (iii) a dynamic threshold that tightens as training progresses, and (iv) a deadline mechanism that boosts long-unselected clients. We also weight aggregation by client data quality and historical performance. Experiments on MNIST and CIFAR-10 under IID and non-IID partitions demonstrate that FedAR achieves faster convergence, higher accuracy, and lower loss than FedAvg and FedProx, while encouraging fairer and more diverse participation. These gains demonstrate that multi-factor, fairness-aware selection can improve both effectiveness and efficiency in real-world FL deployments.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Hayyolalam, V., & Özkasap, Ö. (2026). FedAR: Adaptive Client Selection Strategy for Heterogeneous Federated Learning. International Conference on Communications, 1–6. https://doi.org/10.1109/icc59461.2026.11588258
MLA 9
Hayyolalam, Vahideh, and Öznur Özkasap. “FedAR: Adaptive Client Selection Strategy for Heterogeneous Federated Learning.” International Conference on Communications, 2026, pp. 1–6. https://doi.org/10.1109/icc59461.2026.11588258.
Chicago
Hayyolalam, Vahideh and Öznur Özkasap. 2026. “FedAR: Adaptive Client Selection Strategy for Heterogeneous Federated Learning.” International Conference on Communications: 1–6. https://doi.org/10.1109/icc59461.2026.11588258.
Harvard
Hayyolalam, V. and Özkasap, Ö. (2026) ‘FedAR: Adaptive Client Selection Strategy for Heterogeneous Federated Learning’, International Conference on Communications, pp. 1–6. doi:10.1109/icc59461.2026.11588258.
IEEE
V. Hayyolalam and Ö. Özkasap, “FedAR: Adaptive Client Selection Strategy for Heterogeneous Federated Learning,” International Conference on Communications, pp. 1–6, 2026, doi: 10.1109/icc59461.2026.11588258.
BibTeX
@inproceedings{hayyolalam2026fedar,
title = {{FedAR: Adaptive Client Selection Strategy for Heterogeneous Federated Learning}},
author = {Hayyolalam, Vahideh and Özkasap, Öznur},
booktitle = {International Conference on Communications},
year = {2026},
pages = {1--6},
doi = {10.1109/icc59461.2026.11588258},
url = {https://doi.org/10.1109/icc59461.2026.11588258}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- federated learning
- adaptive client selection
- heterogeneous clients
- non-IID data
- communication efficiency
- aging mechanisms
- weighted aggregation
- convergence rate
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Hayyolalam, V., & Özkasap, Ö. (2026). FedAR: Adaptive Client Selection Strategy for Heterogeneous Federated Learning. International Conference on Communications, 1–6. https://doi.org/10.1109/icc59461.2026.11588258
How many times has this paper been cited?
0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at International Conference on Communications: sign in and open the full text from this page.
Who wrote this paper?
Vahideh Hayyolalam, Öznur Özkasap.
What is the DOI of this paper?
10.1109/icc59461.2026.11588258, permanently at https://doi.org/10.1109/icc59461.2026.11588258. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.