Split Federated Learning

Split Federated Learning (SFL) is a distributed machine learning approach that divides a model between clients and a server to collaboratively train a shared model while minimizing individual client computational burdens and preserving data privacy. Current research focuses on addressing challenges like asynchronous communication, adversarial attacks (especially on large language models), and data heterogeneity through techniques such as generative activation-aided updates, jamming-resilient frameworks, and adaptive model splitting strategies. SFL's significance lies in its potential to enable efficient and privacy-preserving training of large models on resource-constrained devices, with applications ranging from vehicular edge computing to continuous authentication and medical image analysis.

Papers

September 2, 2024

GAS: Generative Activation-Aided Asynchronous Split Federated Learning
Jiarong Yang, Yuan Liu
Generative Network Asynchronous Federated Learning Split Federated Learning Asynchronous Stochastic Gradient Descent

July 16, 2024

R-SFLLM: Jamming Resilient Framework for Split Federated Learning with Large Language Models
Aladin Djuhera, Vlad C. Andrei, Xinyang Li, Ullrich J. Mönich, Holger Boche, Walid Saad
Split Federated Learning Anti Jamming

June 12, 2024

A deep cut into Split Federated Self-supervised Learning
Marcin Przewięźlikowski, Marcin Osial, Bartosz Zieliński, Marek Śmieja
Self Supervised Learning Momentum Based Cut and Approximate Split Federated Learning Federated Split Learning Depth Separation Network Layer

May 29, 2024

May 12, 2024

CRSFL: Cluster-based Resource-aware Split Federated Learning for Continuous Authentication
Mohamad Wazzeh, Mohamad Arafeh, Hani Sami, Hakima Ould-Slimane, Chamseddine Talhi, Azzam Mourad, Hadi Otrok
Split Learning Decentralized Machine Learning Split Federated Learning Continuous Authentication

May 8, 2024

SCALA: Split Federated Learning with Concatenated Activations and Logit Adjustments
Jiarong Yang, Yuan Liu
Label Distribution Targeted Activation Penalty Machine Learning Framework Split Federated Learning Logit Adjustment Label Variation

April 19, 2024

KoReA-SFL: Knowledge Replay-based Split Federated Learning Against Catastrophic Forgetting
Zeke Xia, Ming Hu, Dengke Yan, Ruixuan Liu, Anran Li, Xiaofei Xie, Mingsong Chen
Catastrophic Forgetting Knowledge Based Model Aggregation Split Federated Learning Knowledge Replay

March 19, 2024

AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networks
Zheng Lin, Guanqiao Qu, Wei Wei, Xianhao Chen, Kin K. Leung
Edge Device Split Federated Learning Resource Constrained Edge Model Splitting Training Convergence

February 24, 2024

ESFL: Efficient Split Federated Learning over Resource-Constrained Heterogeneous Wireless Devices
Guangyu Zhu, Yiqin Deng, Xianhao Chen, Haixia Zhang, Yuguang Fang, Tan F. Wong
Machine Learning Model Split Learning Split Federated Learning Splitfed Learning Optimal Split

February 23, 2024

Convergence Analysis of Split Federated Learning on Heterogeneous Data
Pengchao Han, Chao Huang, Geng Tian, Ming Tang, Xin Liu
Model Training Convergence Analysis Heterogeneous Data Non Convex Objective Split Federated Learning Convex Objective

January 16, 2024

HierSFL: Local Differential Privacy-aided Split Federated Learning in Mobile Edge Computing
Minh K. Quan, Dinh C. Nguyen, Van-Dinh Nguyen, Mayuri Wijayasundara, Sujeeva Setunge, Pubudu N. Pathirana
Model Training Local Differential Privacy Mobile Edge Computing Local Gradient Split Federated Learning

December 18, 2023

MISA: Unveiling the Vulnerabilities in Split Federated Learning
Wei Wan, Yuxuan Ning, Shengshan Hu, Lulu Xue, Minghui Li, Leo Yu Zhang, Hai Jin
Native Robustness Poisoning Attack Security Vulnerability Global Model Split Federated Learning

November 22, 2023

November 15, 2023

Exploring the Privacy-Energy Consumption Tradeoff for Split Federated Learning
Joohyung Lee, Mohamed Seif, Jungchan Cho, H. Vincent Poor
Split Learning Privacy Utility Split Federated Learning Layer Selection

November 8, 2023

Edge-assisted U-Shaped Split Federated Learning with Privacy-preserving for Internet of Things
Hengliang Tang, Zihang Zhao, Detian Liu, Yang Cao, Shiqiang Zhang, Siqing You
Split Learning Internet of Thing Device Good Thing Split Federated Learning Edge Assisted

October 24, 2023

Accelerating Split Federated Learning over Wireless Communication Networks
Ce Xu, Jinxuan Li, Yuan Liu, Yushi Ling, Miaowen Wen
Deep Neural Network Split Learning Parallel Training Split Federated Learning Model Splitting Model Partition

July 29, 2023

Efficient Semi-Supervised Federated Learning for Heterogeneous Participants
Zhipeng Sun, Yang Xu, Hongli Xu, Zhiyuan Wang, Yunming Liao
Semi Supervised Model Training Split Federated Learning Robust Clustering Heterogeneous Participant

July 25, 2023

SplitFed resilience to packet loss: Where to split, that is the question
Chamani Shiranthika, Zahra Hafezi Kafshgari, Parvaneh Saeedi, Ivan V. Bajić
Yes No Question Split Learning Interest Loss Decentralized Machine Learning Split Federated Learning Splitfed Learning

Split Federated Learning

Papers

GAS: Generative Activation-Aided Asynchronous Split Federated Learning

R-SFLLM: Jamming Resilient Framework for Split Federated Learning with Large Language Models

A deep cut into Split Federated Self-supervised Learning

Optimizing Split Points for Error-Resilient SplitFed Learning

Adaptive and Parallel Split Federated Learning in Vehicular Edge Computing

CRSFL: Cluster-based Resource-aware Split Federated Learning for Continuous Authentication

SCALA: Split Federated Learning with Concatenated Activations and Logit Adjustments

KoReA-SFL: Knowledge Replay-based Split Federated Learning Against Catastrophic Forgetting

AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networks

ESFL: Efficient Split Federated Learning over Resource-Constrained Heterogeneous Wireless Devices

Convergence Analysis of Split Federated Learning on Heterogeneous Data

HierSFL: Local Differential Privacy-aided Split Federated Learning in Mobile Edge Computing

MISA: Unveiling the Vulnerabilities in Split Federated Learning

MergeSFL: Split Federated Learning with Feature Merging and Batch Size Regulation

Have Your Cake and Eat It Too: Toward Efficient and Accurate Split Federated Learning

Exploring the Privacy-Energy Consumption Tradeoff for Split Federated Learning

Edge-assisted U-Shaped Split Federated Learning with Privacy-preserving for Internet of Things

Accelerating Split Federated Learning over Wireless Communication Networks

Efficient Semi-Supervised Federated Learning for Heterogeneous Participants

SplitFed resilience to packet loss: Where to split, that is the question