Conference paper · 2026 · Open access

Reliability-Aware Client Selection in Asynchronous and Heterogeneous Federated Learning

Arya Wicaksana, Bayu Anggorojati, Muhamad Erza Aminanto, Agustian Taufiq Asyhari

International Conference on Future Internet of Things and Cloud (FiCloud), 273–278 · Published 1 July 2026 · DOI 10.1109/ficloud70576.2026.00044

Open full textCite this paper

In brief

“Reliability-Aware Client Selection in Asynchronous and Heterogeneous Federated Learning” is a 2026 conference paper by Arya Wicaksana and 3 co-authors, published in International Conference on Future Internet of Things and Cloud (FiCloud). 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 Future Internet of Things and Cloud (FiCloud).

Citations
0
References
16
Authors
4

Abstract

Polaris is a client selection framework for asynchronous and heterogeneous federated learning that employs quality-aware sampling to accelerate convergence. Its reliance on scalar update norms as quality indicators exposes it to exploitation, in which clients submit near-zero Gaussian updates that inflate the update magnitude proxy within the Polaris sampling objective without contributing meaningful gradient information. This work introduces a lightweight reliability-aware extension that embeds two server-side signals, Exponential Moving Average (EMA)-based magnitude credibility and cosine similarity-based directional alignment, directly into the staleness and aggregation weight proxy computation without modifying the geometric programming objective or aggregation semantics. Experiments across ResNet-18 on CIFAR-10, LeNet-5 on FEMNIST, and LeNet-5 on MNIST under non-IID data distributions confirm that attack effectiveness and defense discrimination are governed by task complexity and non-IID (non-Independent and Identically Distributed) degree. The proposed method demonstrates partial resistance to convergence collapse at lower adversarial ratios while introducing only a marginal accuracy overhead under clean conditions.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Wicaksana, A., Anggorojati, B., Aminanto, M. E., & Asyhari, A. T. (2026). Reliability-Aware Client Selection in Asynchronous and Heterogeneous Federated Learning. International Conference on Future Internet of Things and Cloud (FiCloud), 273–278. https://doi.org/10.1109/ficloud70576.2026.00044

MLA 9

Wicaksana, Arya, et al. “Reliability-Aware Client Selection in Asynchronous and Heterogeneous Federated Learning.” International Conference on Future Internet of Things and Cloud (FiCloud), 2026, pp. 273–278. https://doi.org/10.1109/ficloud70576.2026.00044.

Chicago

Wicaksana, Arya, Bayu Anggorojati, Muhamad Erza Aminanto, and Agustian Taufiq Asyhari. 2026. “Reliability-Aware Client Selection in Asynchronous and Heterogeneous Federated Learning.” International Conference on Future Internet of Things and Cloud (FiCloud): 273–278. https://doi.org/10.1109/ficloud70576.2026.00044.

Harvard

Wicaksana, A. et al. (2026) ‘Reliability-Aware Client Selection in Asynchronous and Heterogeneous Federated Learning’, International Conference on Future Internet of Things and Cloud (FiCloud), pp. 273–278. doi:10.1109/ficloud70576.2026.00044.

IEEE

A. Wicaksana, B. Anggorojati, M. E. Aminanto, and A. T. Asyhari, “Reliability-Aware Client Selection in Asynchronous and Heterogeneous Federated Learning,” International Conference on Future Internet of Things and Cloud (FiCloud), pp. 273–278, 2026, doi: 10.1109/ficloud70576.2026.00044.

BibTeX

@inproceedings{wicaksana2026reliability,
  title     = {{Reliability-Aware Client Selection in Asynchronous and Heterogeneous Federated Learning}},
  author    = {Wicaksana, Arya and Anggorojati, Bayu and Aminanto, Muhamad Erza and Asyhari, Agustian Taufiq},
  booktitle = {International Conference on Future Internet of Things and Cloud (FiCloud)},
  year      = {2026},
  pages     = {273--278},
  doi       = {10.1109/ficloud70576.2026.00044},
  url       = {https://doi.org/10.1109/ficloud70576.2026.00044}
}

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

  • client selection
  • asynchronous federated learning
  • heterogeneous federated learning
  • Polaris
  • staleness
  • aggregation weights
  • non-IID data
  • adversarial attacks

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Wicaksana, A., Anggorojati, B., Aminanto, M. E., & Asyhari, A. T. (2026). Reliability-Aware Client Selection in Asynchronous and Heterogeneous Federated Learning. International Conference on Future Internet of Things and Cloud (FiCloud), 273–278. https://doi.org/10.1109/ficloud70576.2026.00044

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 Future Internet of Things and Cloud (FiCloud): sign in and open the full text from this page.

Who wrote this paper?

Arya Wicaksana, Bayu Anggorojati, Muhamad Erza Aminanto, Agustian Taufiq Asyhari.

What is the DOI of this paper?

10.1109/ficloud70576.2026.00044, permanently at https://doi.org/10.1109/ficloud70576.2026.00044. 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.