Scholarlink

Federated Learning (FL) enables decentralized model training across distributed devices while preserving data privacy. However, client heterogeneity, communication bottlenecks, and dynamic resource availability pose substantial challenges. Deep Reinforcement Learning (DRL) offers a powerful framework for adaptive client selection and resource allocation in such environments. This survey examines DRL-driven strategies across centralized, hierarchical (HFL), cross-silo (CSFL), and edge-based (FEEL) FL architectures. We categorize and analyze both single-agent and multi-agent DRL approaches, evaluating them on complexity, scalability, fairness, and communication efficiency. Our study aims to guide the design of robust, scalable FL systems optimized via DRL under heterogeneous real-world conditions.

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

Deep Reinforcement Learning for Client Selection and Resource Allocation in Federated Learning: A Comprehensive Survey

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mohammed Amir Messioud,
  • Abdelhamid Malki,
  • Samir Ouchani

摘要

Federated Learning (FL) enables decentralized model training across distributed devices while preserving data privacy. However, client heterogeneity, communication bottlenecks, and dynamic resource availability pose substantial challenges. Deep Reinforcement Learning (DRL) offers a powerful framework for adaptive client selection and resource allocation in such environments. This survey examines DRL-driven strategies across centralized, hierarchical (HFL), cross-silo (CSFL), and edge-based (FEEL) FL architectures. We categorize and analyze both single-agent and multi-agent DRL approaches, evaluating them on complexity, scalability, fairness, and communication efficiency. Our study aims to guide the design of robust, scalable FL systems optimized via DRL under heterogeneous real-world conditions.