• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Transactions on Parallel and Distributed Systems >An Efficiency-Boosting Client Selection Scheme for Federated Learning With Fairness Guarantee
【24h】

An Efficiency-Boosting Client Selection Scheme for Federated Learning With Fairness Guarantee

机译：具有公平保证的联合学习的效率促进客户选择方案

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The issue of potential privacy leakage during centralized AI's model training has drawn intensive concern from the public. A Parallel and Distributed Computing (or PDC) scheme, termed Federated Learning (FL), has emerged as a new paradigm to cope with the privacy issue by allowing clients to perform model training locally, without the necessity to upload their personal sensitive data. In FL, the number of clients could be sufficiently large, but the bandwidth available for model distribution and re-upload is quite limited, making it sensible to only involve part of the volunteers to participate in the training process. The client selection policy is critical to an FL process in terms of training efficiency, the final model's quality as well as fairness. In this article, we will model the fairness guaranteed client selection as a Lyapunov optimization problem and then a C(2)MAB-based method is proposed for estimation of the model exchange time between each client and the server, based on which we design a fairness guaranteed algorithm termed RBCS-F for problem-solving. The regret of RBCS-F is strictly bounded by a finite constant, justifying its theoretical feasibility. Barring the theoretical results, more empirical data can be derived from our real training experiments on public datasets.
机译：集中AI模型培训期间潜在隐私泄漏的问题已经吸引了公众的强烈关注。并行和分布式计算（或PDC）方案被称为联合学习（FL），它被允许客户在本地执行模型培训，以应对隐私问题的新范式出现为新的范例，而无需上传其个人敏感数据的必要性。在FL中，客户的数量可能是足够大的，但可用于模型分布和重新上传的带宽非常有限，使得只涉及部分志愿者参与培训过程。客户选择政策对于培训效率，最终模型的质量和公平性至关重要。在本文中，我们将根据Lyapunov优化问题模拟公平保证客户选择，然后提出了C（2）基于MAB的方法，以估计每个客户端和服务器之间的模型交换时间，基于我们设计a公平保证算法被称为解决问题的RBCS-F. RBCS-F的遗憾受到有限常数，致力于理论可行性的限制。禁止理论结果，更多的经验数据可以从我们的公共数据集的真实培训实验中源。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号