In this research, we investigate the barriers associated with implementing Federated Learning (FL) in real-world scenarios, where a consistent connection between the central server and all clients cannot be maintained, and data distribution is heterogeneous. To address these challenges, we focus on mobilizing the federated setting, where the server moves between groups of adjacent clients to learn local models. Specifically, we propose a new algorithm, Random Walk Stochastic Alternating Direction Method of Multipliers (RWSADMM), capable of adapting to dynamic and ad-hoc network conditions as long as a sufficient number of connected clients are available for model training. In RWSADMM, the server walks randomly toward a group of clients. It formulates local proximity among adjacent clients based on hard inequality constraints instead of consensus updates to address data heterogeneity. Our proposed method is convergent, reduces communication costs, and enhances scalability by reducing the number of clients the central server needs to communicate with.

翻译：本研究探讨了在现实场景中部署联邦学习（FL）时面临的障碍，即在中央服务器与所有客户端之间无法维持稳定连接且数据分布呈异质性的情况下所存在的问题。针对这些挑战，我们聚焦于一种可移动的联邦学习设置，其中服务器在相邻客户端群组间移动以学习局部模型。具体而言，我们提出了一种新算法——随机游走随机交替方向乘子法（RWSADMM），该算法能够适应动态和自组织网络条件，只要存在足够数量的连接客户端即可进行模型训练。在RWSADMM中，服务器随机向一组客户端移动。该方法基于硬性不等式约束建立相邻客户端间的局部邻近关系，而非采用共识更新策略，从而应对数据异质性。所提出的算法具有收敛性，能够降低通信成本，并通过减少中央服务器需通信的客户端数量来增强可扩展性。