paper-with-me

홈 › Papers

Accelerating Federated Split Learning via Local-Loss-Based Training

2021-09-29 · Dong-Jun Han, Hasnain Irshad Bhatti, Jungmoon Lee, Jaekyun Moon

Federated learning (FL) operates based on model exchanges between the server and the clients, and suffers from significant communication as well as client-side computation burden. Emerging split learning (SL) solutions can reduce the clientside computation burden by splitting the model architecture between the server and the clients. However, SL-based ideas still require significant time delay, since each participating client should wait for the backpropagated gradients from the server in order to update its model. Also, the communication burden can still be substantial, depending on various factors like local dataset size and shape of cut layer activations/gradients. In this paper, we propose a new direction to FL/SL based on updating the client/server-side models in parallel, via local-loss-based training specifically geared to split learning. The parallel training of split models substantially shortens latency while obviating server-to-clients communication. We provide latency analysis that leads to optimal model cut as well as general guidelines for splitting the model. We also provide a theoretical analysis for guaranteeing convergence and understanding interplay among different hyperparameters and system constraints. Extensive experimental results indicate that our scheme has significant communication and latency advantages over existing FL and SL ideas.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

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

2025-05-29 · Srijith Nair, Michael Lin, Amirreza Talebi, Peizhong Ju 외

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 f…

Federated Learning

Accelerating Split Federated Learning over Wireless Communication Networks

2023-10-24 · Ce Xu, Jinxuan Li, YuAn Liu, Yushi Ling 외

The development of artificial intelligence (AI) provides opportunities for the promotion of deep neural network (DNN)-based applications. However, the large amount of parameters and computational complexity of DNN makes …

Federated Learning

Accelerating Wireless Distributed Learning via Hybrid Split and Federated Learning Optimization

2025-11-25 · Kun Guo, Xuefei Li, Xijun Wang, Howard H. Yang 외 arxiv

Federated learning (FL) and split learning (SL) are two effective distributed learning paradigms in wireless networks, enabling collaborative model training across mobile devices without sharing raw data. While FL suppor…

Federated Learning

Federated Split BERT for Heterogeneous Text Classification

2022-05-26 · Zhengyang Li, Shijing Si, Jianzong Wang, Jing Xiao

Pre-trained BERT models have achieved impressive performance in many natural language processing (NLP) tasks. However, in many real-world situations, textual data are usually decentralized over many clients and unable to…

ClassificationFederated LearningQuantizationtext-classification+1

Robust Split Federated Learning for U-shaped Medical Image Networks

2022-12-13 · Ziyuan Yang, Yingyu Chen, Huijie Huangfu, Maosong Ran 외

U-shaped networks are widely used in various medical image tasks, such as segmentation, restoration and reconstruction, but most of them usually rely on centralized learning and thus ignore privacy issues. To address the…

Federated Learning