Scholarlink

In this paper, we propose a blockchain-based federated learning framework with client selection and a round-based training scheme (BFCSR). The framework contains three modules to help federated learning achieve better performance. The blockchain module provides defenses against data tampering and single-point failure. The client selection module selects high-quality clients to participate in the training. The round-based training module puts a time threshold on the training time to reduce the clients’ waiting time, improving overall performance. Comparison experiments to several baselines and results show that our framework performs better in various experiment settings.

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

BFCSR: A Blockchain-Based Federated Learning Framework with Client Selection and Round-Based Training Scheme

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Zijie Zhao,
  • Xing He,
  • Xinyu Ruan,
  • Chenpei Wang,
  • Yuan Liu,
  • Xiaohui Zhong,
  • Yang Yue,
  • Ruhui Ma,
  • Jinshan Sun

摘要

In this paper, we propose a blockchain-based federated learning framework with client selection and a round-based training scheme (BFCSR). The framework contains three modules to help federated learning achieve better performance. The blockchain module provides defenses against data tampering and single-point failure. The client selection module selects high-quality clients to participate in the training. The round-based training module puts a time threshold on the training time to reduce the clients’ waiting time, improving overall performance. Comparison experiments to several baselines and results show that our framework performs better in various experiment settings.