主题：PFed-NS: an Adaptive Personalized Federated Learning Scheme through Neural Network Segmentation

嘉宾：何黎刚  华威大学计算机系Reader

时间：2026年4月14日 下午15:00-16:00

地点：华中科技大学东五楼210学术报告厅

报告摘要：

Federated Learning (FL) is typically deployed in a client-server architecture, which makes the Edge-Cloud ar- chitecture an ideal backbone for FL. A significant challenge in this setup arises from the diverse data feature distributions across different edge locations (i.e., non-IID data). In response, Personalized Federated Learning (PFL) approaches have been developed. Network segmentation-based PFL is an important approach to achieving PFL, in which the training network is divided into a global segment for server aggregation and a local segment maintained client-side. Existing methods determine the segmentation before the training, and the segmentation remains fixed throughout the PFL training. However, our investigation reveals that model representations vary as PFL progresses and the fixed segmentation may not deliver best performance across various training settings. To address this, we propose PFed-NS, a PFL framework based on adaptive network segmentation. This adaptive segmentation technique is composed of two elements: a mechanism for assessing divergence of clients’ probability density functions constructed from network layers’ outputs, and a model for dynamically establishing divergence thresholds, beyond which server aggregation is deemed detrimental. Further optimization strategies are proposed to reduce the computation and com- munication costs incurred by divergence modeling. Moreover, we propose a divergence-based BN strategy to optimize BN performance for network segmentation-based PFL. Extensive experiments have been conducted to compare PFed-NS against recent PFL models. The results demonstrate its superiority in enhancing model accuracy and accelerating convergence.

报告人简介：

何黎刚博士本科和硕士毕业于华中科技大学，博士毕业于英国华威大学计算机系，并在剑桥大学进行博士后研究。现为华威大学计算机系Reader。当前的研究方向包括并行或分布式机器/深度学习（例如联邦学习、图神经网络训练加速）、集群、云计算和边缘计算（例如，优化工作负载和资源管理解决方案）、并行化/分布式数据分析方法（例如，时间序列数据的异常检测、点云的深度学习方法、大数据的模式发现），以及并行与分布式系统中的杂项问题（例如，在分布式系统中优化通信方案、有安全约束的高性能计算）。ScholarGPS2024 榜单分布式计算领域全球前0.5%学者。在国际期刊和会议上（例如IEEE TC, TPDS, TKDE, TCSVT, NeurIPS, SC, ICDCS, IPDPS, ICPP, HPCA, EuroSys）发表论文200余篇，并且多次获得最佳论文奖（例如在联邦学习领域的论文获得2021年度IEEE Transactions on Computers期刊的最佳论文奖第二名）。主持和承担过英国、欧盟及企业界多个研究项目。