Federated Learning (FL) is a promising privacy-preserving distributed machine learning paradigm. However, communication inefficiency remains the key bottleneck that impedes its large-scale implementation. Recently, hierarchical FL (HFL) has been proposed in which data owners, i.e., workers, can first transmit their updated model parameters to edge servers for intermediate aggregation. This reduces the instances of global communication and straggling workers. To enable efficient HFL, it is important to address the issues of edge association and resource allocation in the context of non-cooperative players, i.e., workers, edge servers, and model owner. However, the existing studies merely focus on static approaches and do not consider the dynamic interactions and bounded rationalities of the players. In this paper, we propose a hierarchical game framework to study the dynamics of edge association and resource allocation in self-organizing HFL networks. In the lower-level game, the edge association strategies of the workers are modelled using an evolutionary game. In the upper-level game, a Stackelberg differential game is adopted in which the model owner decides an optimal reward scheme given the expected bandwidth allocation control strategy of the edge server. Finally, we provide numerical results to validate that our proposed framework captures the HFL system dynamics under varying sources of network heterogeneity.

中文翻译：

---

自组织分层联邦学习网络中的动态边缘关联和资源分配

联邦学习（FL）是一种很有前途的隐私保护分布式机器学习范式。然而，沟通效率低下仍然是阻碍其大规模实施的关键瓶颈。最近，已经提出了分层 FL (HFL)，其中数据所有者，即工作人员，可以首先将他们更新的模型参数传输到边缘服务器以进行中间聚合。这减少了全局通信和分散工作人员的情况。为了实现高效的 HFL，重要的是在非合作参与者（即工人、边缘服务器和模型所有者）的背景下解决边缘关联和资源分配问题。然而，现有的研究只关注静态方法，没有考虑参与者的动态交互和有限理性。在本文中，我们提出了一个分层博弈框架来研究自组织 HFL 网络中边缘关联和资源分配的动态。在较低级别的博弈中，工人的边缘关联策略使用进化博弈进行建模。在上层博弈中，采用 Stackelberg 微分博弈，模型所有者在给定边缘服务器的预期带宽分配控制策略的情况下决定最优奖励方案。最后，我们提供数值结果来验证我们提出的框架在不同网络异质性来源下捕获 HFL 系统动态。采用 Stackelberg 微分博弈，模型所有者在给定边缘服务器的预期带宽分配控制策略的情况下决定最佳奖励方案。最后，我们提供数值结果来验证我们提出的框架在不同网络异质性来源下捕获 HFL 系统动态。采用 Stackelberg 微分博弈，模型所有者在给定边缘服务器的预期带宽分配控制策略的情况下决定最佳奖励方案。最后，我们提供数值结果来验证我们提出的框架在不同网络异质性来源下捕获 HFL 系统动态。