标题： SAFL：通过客户端特定聚类和SCSI引导的模型剪枝的结构感知个性化联邦学习 显示英文标题

标题： SAFL: Structure-Aware Personalized Federated Learning via Client-Specific Clustering and SCSI-Guided Model Pruning

摘要： 联邦学习（FL）使客户端能够在不共享本地数据的情况下协作训练机器学习模型，从而在各种环境中保护隐私。 虽然传统的FL方法保护隐私，但它们常常面临高计算和通信开销的问题。 为了解决这些问题，引入了模型剪枝作为一种优化计算的策略。 然而，现有的剪枝方法仅基于本地数据时，通常会产生无法充分反映客户端特定任务的子模型，这是由于数据不足所致。 为了克服这些挑战，本文介绍了SAFL（结构感知联邦学习），一种通过客户端特定聚类和相似客户端结构信息（SCSI）引导的模型剪枝来增强个性化联邦学习的新框架。 SAFL采用两阶段过程：首先，根据数据相似性对客户端进行分组，并使用聚合的剪枝标准来指导剪枝过程，有助于识别最优子模型。 随后，客户端训练这些剪枝后的模型并参与基于服务器的聚合，确保每个客户端都有定制且高效的模型。 该方法显著降低了计算开销，同时提高了推理准确性。 大量实验表明，SAFL明显减小了模型大小并提高了性能，使其在具有异构数据的联邦环境中非常有效。 显示英文摘要

摘要： Federated Learning (FL) enables clients to collaboratively train machine learning models without sharing local data, preserving privacy in diverse environments. While traditional FL approaches preserve privacy, they often struggle with high computational and communication overhead. To address these issues, model pruning is introduced as a strategy to streamline computations. However, existing pruning methods, when applied solely based on local data, often produce sub-models that inadequately reflect clients' specific tasks due to data insufficiency. To overcome these challenges, this paper introduces SAFL (Structure-Aware Federated Learning), a novel framework that enhances personalized federated learning through client-specific clustering and Similar Client Structure Information (SCSI)-guided model pruning. SAFL employs a two-stage process: initially, it groups clients based on data similarities and uses aggregated pruning criteria to guide the pruning process, facilitating the identification of optimal sub-models. Subsequently, clients train these pruned models and engage in server-based aggregation, ensuring tailored and efficient models for each client. This method significantly reduces computational overhead while improving inference accuracy. Extensive experiments demonstrate that SAFL markedly diminishes model size and improves performance, making it highly effective in federated environments characterized by heterogeneous data.