paper-with-me

홈 › Papers

FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient Estimation

2025-05-29 · Srijith Nair, Michael Lin, Amirreza Talebi, Peizhong Ju, Elizabeth Bentley, Jia Liu

Collaborative training methods like Federated Learning (FL) and Split Learning (SL) enable distributed machine learning without sharing raw data. However, FL assumes clients can train entire models, which is infeasible for large-scale models. In contrast, while SL alleviates the client memory constraint in FL by offloading most training to the server, it increases network latency due to its sequential nature. Other methods address the conundrum by using local loss functions for parallel client-side training to improve efficiency, but they lack server feedback and potentially suffer poor accuracy. We propose FSL-SAGE (Federated Split Learning via Smashed Activation Gradient Estimation), a new federated split learning algorithm that estimates server-side gradient feedback via auxiliary models. These auxiliary models periodically adapt to emulate server behavior on local datasets. We show that FSL-SAGE achieves a convergence rate of $\mathcal{O}(1/\sqrt{T})$, where $T$ is the number of communication rounds. This result matches FedAvg, while significantly reducing communication costs and client memory requirements. Our empirical results also verify that it outperforms existing state-of-the-art FSL methods, offering both communication efficiency and accuracy.

📄 PDF Abstract BibTeX arXiv:2505.23182

Code (1)

srijith1996/FSL-SAGE 공식 구현 pytorch

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Visual Transformer Meets CutMix for Improved Accuracy, Communication Efficiency, and Data Privacy in Split Learning

2022-07-01 · Sihun Baek, Jihong Park, Praneeth Vepakomma, Ramesh Raskar 외

This article seeks for a distributed learning solution for the visual transformer (ViT) architectures. Compared to convolutional neural network (CNN) architectures, ViTs often have larger model sizes, and are computation…

Data AugmentationFederated Learning

Federated Split Learning with Improved Communication and Storage Efficiency

2025-07-21 · Yujia Mu, Cong Shen arxiv

Federated learning (FL) is one of the popular distributed machine learning (ML) solutions but incurs significant communication and computation costs at edge devices. Federated split learning (FSL) can train sub-models in…

Federated Learning

SL-ACC: A Communication-Efficient Split Learning Framework with Adaptive Channel-wise Compression

2025-08-18 · Zehang Lin, Zheng Lin, Miao Yang, Jianhao Huang 외 arxiv

The increasing complexity of neural networks poses a significant barrier to the deployment of distributed machine learning (ML) on resource-constrained devices, such as federated learning (FL). Split learning (SL) offers…

Federated Learning

HealSplit: Towards Self-Healing through Adversarial Distillation in Split Federated Learning

2025-11-14 · Yuhan Xie, Chen Lyu arxiv

Split Federated Learning (SFL) is an emerging paradigm for privacy-preserving distributed learning. However, it remains vulnerable to sophisticated data poisoning attacks targeting local features, labels, smashed data, a…

Federated Learning

Differentially Private CutMix for Split Learning with Vision Transformer

2022-10-28 · Seungeun Oh, Jihong Park, Sihun Baek, Hyelin Nam 외

Recently, vision transformer (ViT) has started to outpace the conventional CNN in computer vision tasks. Considering privacy-preserving distributed learning with ViT, federated learning (FL) communicates models, which be…

Federated LearningPrivacy Preserving