Splitfed Learning

SplitFed learning is a hybrid approach combining federated and split learning to train machine learning models collaboratively across distributed devices while minimizing individual device computational burdens and preserving data privacy. Current research focuses on optimizing model splitting strategies (e.g., determining optimal "cut layers"), improving robustness to communication issues (like packet loss) and non-IID data, and enhancing efficiency across heterogeneous devices. This framework shows promise for deploying complex models, such as large language models, on resource-constrained devices, particularly in applications like IoT and edge computing, by significantly reducing training time and improving model accuracy compared to traditional federated learning.

Papers

July 12, 2024

FedsLLM: Federated Split Learning for Large Language Models over Communication Networks
Kai Zhao, Zhaohui Yang, Chongwen Huang, Xiaoming Chen, Zhaoyang Zhang
Large Language Model Low Rank Adaptation Split Learning Computer Network Federated Split Learning Splitfed Learning

May 29, 2024

Optimizing Split Points for Error-Resilient SplitFed Learning
Chamani Shiranthika, Parvaneh Saeedi, Ivan V. Bajić
Split Learning Split and Fit Split Federated Learning Splitfed Learning

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

August 23, 2023

When MiniBatch SGD Meets SplitFed Learning:Convergence Analysis and Performance Evaluation
Chao Huang, Geng Tian, Ming Tang
Convergence Analysis Gradient Norm Performance Evaluation Splitfed Learning Minibatch SGD

July 25, 2023

July 4, 2023

Analyzing the vulnerabilities in SplitFed Learning: Assessing the robustness against Data Poisoning Attacks
Aysha Thahsin Zahir Ismail, Raj Mani Shukla
Native Robustness Security Vulnerability Split Learning Data Poisoning Attack Splitfed Learning

April 28, 2023

Quality-Adaptive Split-Federated Learning for Segmenting Medical Images with Inaccurate Annotations
Zahra Hafezi Kafshgari, Chamani Shiranthika, Parvaneh Saeedi, Ivan V. Bajić
Split Learning Medical Segmentation Annotation Error Split Federated Learning Averaging Algorithm Splitfed Learning

December 4, 2022

Security Analysis of SplitFed Learning
Momin Ahmad Khan, Virat Shejwalkar, Amir Houmansadr, Fatima Muhammad Anwar
Split Learning Model Poisoning Attack Splitfed Learning

October 4, 2022

Split Federated Learning on Micro-controllers: A Keyword Spotting Showcase
Jingtao Li, Runcong Kuang
Keyword Spotting Collaborative Learning Private Learning 32 Bit Microcontrollers Split Federated Learning Mandarin Speech Splitfed Learning

Splitfed Learning

Papers

FedsLLM: Federated Split Learning for Large Language Models over Communication Networks

Optimizing Split Points for Error-Resilient SplitFed Learning

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

When MiniBatch SGD Meets SplitFed Learning:Convergence Analysis and Performance Evaluation

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

Federated Split Learning with Only Positive Labels for resource-constrained IoT environment

Analyzing the vulnerabilities in SplitFed Learning: Assessing the robustness against Data Poisoning Attacks

Quality-Adaptive Split-Federated Learning for Segmenting Medical Images with Inaccurate Annotations

Security Analysis of SplitFed Learning

Split Federated Learning on Micro-controllers: A Keyword Spotting Showcase