# Diversity-Aware Client Selection for Communication-Efficient Federated Learning

DevFeed: [Diversity-Aware Client Selection for Communication-Efficient Federated Learning](<https://devfeed.tech/articles/diversity-aware-client-selection-for-communication-efficient-federated-learning-123388.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09278>)

Author: Max Halleryd, Sima Sinaei, Viktor Valadi, Mina Alibeigi, Henrik Abrahamsson, Salman Toor

Published: 2026-11-09T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [client](<https://devfeed.tech/tags/client.md>), [communication](<https://devfeed.tech/tags/communication.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [selection](<https://devfeed.tech/tags/selection.md>)

## AI overview

The abstract reports that limiting federated learning participation to 15% of clients per round can significantly reduce communication while preserving or improving model quality under non-IID conditions, when client selection encourages diverse, balanced contributions. It compares Power-of-Choice, Fisher information, and Centered Kernel Alignment using accuracy, convergence, and participation-diversity measures including the Gini coefficient and KL divergence. Diversity-promoting selection is reported to improve generalization over biased alternatives. The excerpt gives no strategy-specific results or further experimental details.

## Source excerpt

arXiv:2611.09278v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, making it attractive for privacy-sensitive and bandwidth-constrained applications. A practical challenge in deploying FL is reducing communication overhead while maintaining model performance under heterogeneous, non-IID data distributions. Selecting which subset of clients participates in each training round offers a principled way to address both challenges simultaneously, yet its impact on data diversity and representativeness remains underexplored. In this paper, we investigate three client selection strategies, Power-of-Choice, Fisher information, and Centered Kernel Alignment, evaluating them not only by accuracy and convergence, but through the lens of participation diversity using the Gini coefficient and KL divergence. Under non-IID conditions, restricting participation to 15% of clients per round achieves significant communication savings, and when selection promotes diverse and balanced contributions, it also improves generalization over biased alternatives. This work provides a systematic and reproducible analysis demonstrating that diversity-focused client selection renders communication efficiency and model quality complementary rather than competing objectives.