Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Mingkun, Zhu, Ran, Wang, Qing, Yang, Jie
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2511.09828
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908656013934592
author Yang, Mingkun
Zhu, Ran
Wang, Qing
Yang, Jie
author_facet Yang, Mingkun
Zhu, Ran
Wang, Qing
Yang, Jie
contents Split Federated Learning is a system-efficient federated learning paradigm that leverages the rich computing resources at a central server to train model partitions. Data heterogeneity across silos, however, presents a major challenge undermining the convergence speed and accuracy of the global model. This paper introduces Step-wise Momentum Fusion (SMoFi), an effective and lightweight framework that counteracts gradient divergence arising from data heterogeneity by synchronizing the momentum buffers across server-side optimizers. To control gradient divergence over the training process, we design a staleness-aware alignment mechanism that imposes constraints on gradient updates of the server-side submodel at each optimization step. Extensive validations on multiple real-world datasets show that SMoFi consistently improves global model accuracy (up to 7.1%) and convergence speed (up to 10.25$\times$). Furthermore, SMoFi has a greater impact with more clients involved and deeper learning models, making it particularly suitable for model training in resource-constrained contexts.
format Preprint
id arxiv_https___arxiv_org_abs_2511_09828
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SMoFi: Step-wise Momentum Fusion for Split Federated Learning on Heterogeneous Data
Yang, Mingkun
Zhu, Ran
Wang, Qing
Yang, Jie
Machine Learning
Distributed, Parallel, and Cluster Computing
Split Federated Learning is a system-efficient federated learning paradigm that leverages the rich computing resources at a central server to train model partitions. Data heterogeneity across silos, however, presents a major challenge undermining the convergence speed and accuracy of the global model. This paper introduces Step-wise Momentum Fusion (SMoFi), an effective and lightweight framework that counteracts gradient divergence arising from data heterogeneity by synchronizing the momentum buffers across server-side optimizers. To control gradient divergence over the training process, we design a staleness-aware alignment mechanism that imposes constraints on gradient updates of the server-side submodel at each optimization step. Extensive validations on multiple real-world datasets show that SMoFi consistently improves global model accuracy (up to 7.1%) and convergence speed (up to 10.25$\times$). Furthermore, SMoFi has a greater impact with more clients involved and deeper learning models, making it particularly suitable for model training in resource-constrained contexts.
title SMoFi: Step-wise Momentum Fusion for Split Federated Learning on Heterogeneous Data
topic Machine Learning
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2511.09828