Scholarlink

<p>We introduce Fed-DCSRW, a federated-learning framework that combines three pillars: (i) a decentralized, data-parallel client-clustering stage that computes centroids in parallel to scale and compute efficiently across heterogeneous clients; (ii) a centroid-based, noise-tolerant Roulette-Wheel client-selection strategy; and (iii) end-to-end differential privacy on both loss reports and gradient updates. The parallel clustering phase partitions the distance computations across multiple nodes, rapidly deriving similarity-based centroids without centralized bottlenecks. These centroids then anchor a loss-aware Roulette Wheel that adjusts each round’s participation probabilities: clients with lower (possibly noisy) losses retain a non-zero chance of being chosen, while the overall selection proportion is dynamically adjusted based on real-time global loss trends, enabling the system to respond to performance changes and prevent training stagnation. Experimental results on non-IID datasets show that Fed-DCSRW achieves faster empirical convergence and higher test accuracy compared to standard methods such as FedAvg, Standard Roulette Wheel Selection (RWS), and Utility-Based Probabilistic Selection (Oort). These results demonstrate the effectiveness of a privacy-preserving, centroid-driven selection strategy in addressing data heterogeneity while maintaining strong model performance.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Fed-DCSRW: a privacy-preserving, dynamic client selection framework for heterogeneous federated learning via roulette wheel mechanism

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月3日

查看全文
  • Aline Abboud,
  • Mohamed El Amine Brahmia,
  • Abdelhafid Abouaissa,
  • Ahmad Shahin,
  • Rocks Mazraani

摘要

We introduce Fed-DCSRW, a federated-learning framework that combines three pillars: (i) a decentralized, data-parallel client-clustering stage that computes centroids in parallel to scale and compute efficiently across heterogeneous clients; (ii) a centroid-based, noise-tolerant Roulette-Wheel client-selection strategy; and (iii) end-to-end differential privacy on both loss reports and gradient updates. The parallel clustering phase partitions the distance computations across multiple nodes, rapidly deriving similarity-based centroids without centralized bottlenecks. These centroids then anchor a loss-aware Roulette Wheel that adjusts each round’s participation probabilities: clients with lower (possibly noisy) losses retain a non-zero chance of being chosen, while the overall selection proportion is dynamically adjusted based on real-time global loss trends, enabling the system to respond to performance changes and prevent training stagnation. Experimental results on non-IID datasets show that Fed-DCSRW achieves faster empirical convergence and higher test accuracy compared to standard methods such as FedAvg, Standard Roulette Wheel Selection (RWS), and Utility-Based Probabilistic Selection (Oort). These results demonstrate the effectiveness of a privacy-preserving, centroid-driven selection strategy in addressing data heterogeneity while maintaining strong model performance.