Scholarlink

Federated Learning (FL) enables privacy-preserving collaborative model training across decentralized clients. While adaptive client selection and knowledge distillation (KD) offer potential efficiency gains by monitoring client progress, existing methods lack systematic understanding of pervasive client and data heterogeneity in practical settings. Prevailing FL approaches assume homogeneous clients with equal importance and capability, selected uniformly at random – an assumption contradicted by Critical Learning Periods (CLP) theory, which demonstrates that minor gradient disturbances during early sensitive phases irreparably degrade model accuracy. To address this, we propose the Critical Learning Period-Aware adaptive Framework (CLAF), a novel FL framework for heterogeneous environments. CLAF introduces dual-granularity (coarse- and fine-grained) CLP detection to intelligently optimize client selection and drive adaptive KD strategies. Extensive experiments on diverse models and datasets show CLAF outperforms state-of-the-art methods by up to 22% in accuracy while maintaining robust generalization capabilities.

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

CLAF: A Critical Learning Period-Aware Adaptive Framework for Federated Learning in Heterogeneous Environments

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Shuaiqi Leng,
  • Chaochao Sun,
  • Yuan Peng,
  • HaiYang Ji

摘要

Federated Learning (FL) enables privacy-preserving collaborative model training across decentralized clients. While adaptive client selection and knowledge distillation (KD) offer potential efficiency gains by monitoring client progress, existing methods lack systematic understanding of pervasive client and data heterogeneity in practical settings. Prevailing FL approaches assume homogeneous clients with equal importance and capability, selected uniformly at random – an assumption contradicted by Critical Learning Periods (CLP) theory, which demonstrates that minor gradient disturbances during early sensitive phases irreparably degrade model accuracy. To address this, we propose the Critical Learning Period-Aware adaptive Framework (CLAF), a novel FL framework for heterogeneous environments. CLAF introduces dual-granularity (coarse- and fine-grained) CLP detection to intelligently optimize client selection and drive adaptive KD strategies. Extensive experiments on diverse models and datasets show CLAF outperforms state-of-the-art methods by up to 22% in accuracy while maintaining robust generalization capabilities.