Abstract

Federated Learning (FL) has emerged as a promising approach to addressing issues related to centralized machine learning such as data privacy, security and access. Nevertheless, it also brings new challenges incurred by heterogeneity among data statistical levels, devices and models in the context of multi-level federated learning (MlFed) architecture. In this paper, we conceive a new Personalized Multi-level Federated Learning (PerMl-Fed) framework, which extends existing MlFed architecture with three specialized personalized FL methods to address the three challenges. Specially, we design a Transfer Multi-level Federated Learning (TrMlFed) model to mitigate statistical heterogeneity across multiple layers of FL. We propose an Asynchronous Multi-level Federated Learning (AsMlFed) approach which allows asynchronous update in MlFed, thus alleviating device heterogeneity. We develop a Deep Mutual Multi-level Federated Learning (DmMlFed) method based on the concept of deep mutual learning to tackle model heterogeneity. We evaluate the PerMl-Fed framework and associated technologies on the public Wireless Sensor Data Mining (WISDM) dataset. Initial results demonstrate improved average accuracy of 7 \(\%\) and achieves accuracy ranging from 84 to 92 \(\%\) across eight different hierarchical group structures.

中文翻译：

---

PerMl-Fed：在异构物联网环境中实现个性化多级联合学习以进行活动识别

摘要

联邦学习 (FL) 已成为解决与集中式机器学习相关的问题（例如数据隐私、安全性和访问）的一种有前途的方法。然而，它也带来了多级联邦学习（MlFed）架构背景下数据统计层次、设备和模型之间的异构性带来的新挑战。在本文中，我们构思了一种新的个性化多级联合学习（PerMl-Fed）框架，该框架通过三种专门的个性化 FL 方法扩展了现有的 MlFed 架构，以解决这三个挑战。特别地，我们设计了一个迁移多级联邦学习（TrMlFed）模型来减轻多层 FL 之间的统计异质性。我们提出了一种异步多级联合学习（AsMlFed）方法，该方法允许 MlFed 中的异步更新，从而减轻设备异构性。我们基于深度相互学习的概念开发了一种深度相互多级联邦学习（DmMlFed）方法来解决模型异构性。我们在公共无线传感器数据挖掘 (WISDM) 数据集上评估 PerMl-Fed 框架和相关技术。初步结果表明，在八个不同的层次组结构中，平均准确度提高了 7 %，并达到了 84 到 92 % 的准确度。