Federated Learning (FL) has emerged as a promising framework for distributed training of AI-based services, applications, and network procedures in 6G. One of the major challenges affecting the performance and efficiency of 6G wireless FL systems is the massive scheduling of user devices over resource-constrained channels. In this work, we argue that the uplink scheduling of FL client devices is a problem with a rich relational structure. To address this challenge, we propose a novel, energy-efficient, and importance-aware metric for client scheduling in FL applications by leveraging Unsupervised Graph Representation Learning (UGRL). Our proposed approach introduces a relational inductive bias in the scheduling process and does not require the collection of training feedback information from client devices, unlike state-of-the-art importance-aware mechanisms. We evaluate our proposed solution against baseline scheduling algorithms based on recently proposed metrics in the literature. Results show that, when considering scenarios of nodes exhibiting spatial relations, our approach can achieve an average gain of up to 10% in model accuracy and up to 17 times in energy efficiency compared to state-of-the-art importance-aware policies.

翻译：联邦学习（FL）已成为6G中基于人工智能的服务、应用及网络流程分布式训练的有前景框架。影响6G无线联邦学习系统性能与效率的主要挑战之一，是在资源受限的信道上对用户设备进行大规模调度。本文论证了联邦学习客户端设备的上行调度是一个具有丰富关系结构的问题。为解决该挑战，我们提出了一种新颖的、能量高效的且感知重要性的联邦学习客户端调度度量，通过利用无监督图表示学习（UGRL）实现。所提出的方法在调度过程中引入了关系归纳偏置，且与当前最先进的感知重要性机制不同，无需从客户端设备收集训练反馈信息。我们基于文献中近期提出的度量指标，将所提方案与基线调度算法进行了对比评估。结果表明，在考虑节点间存在空间关系的场景时，与最先进的感知重要性策略相比，本方法在模型准确率上平均提升高达10%，在能量效率上平均提升达17倍。