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

2023-07-25 · Chamani Shiranthika, Zahra Hafezi Kafshgari, Parvaneh Saeedi, Ivan V. Bajić

Decentralized machine learning has broadened its scope recently with the invention of Federated Learning (FL), Split Learning (SL), and their hybrids like Split Federated Learning (SplitFed or SFL). The goal of SFL is to reduce the computational power required by each client in FL and parallelize SL while maintaining privacy. This paper investigates the robustness of SFL against packet loss on communication links. The performance of various SFL aggregation strategies is examined by splitting the model at two points -- shallow split and deep split -- and testing whether the split point makes a statistically significant difference to the accuracy of the final model. Experiments are carried out on a segmentation model for human embryo images and indicate the statistically significant advantage of a deeper split point.

📄 PDF Abstract BibTeX arXiv:2307.13851

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Optimizing Split Points for Error-Resilient SplitFed Learning

2024-05-29 · Chamani Shiranthika, Parvaneh Saeedi, Ivan V. Bajić

Recent advancements in decentralized learning, such as Federated Learning (FL), Split Learning (SL), and Split Federated Learning (SplitFed), have expanded the potentials of machine learning. SplitFed aims to minimize th…

Federated Learning Image Segmentation Semantic Segmentation

Smart Split-Federated Learning over Noisy Channels for Embryo Image Segmentation

2026-01-26 · Zahra Hafezi Kafshgari, Ivan V. Bajic, Parvaneh Saeedi arxiv

Split-Federated (SplitFed) learning is an extension of federated learning that places minimal requirements on the clients computing infrastructure, since only a small portion of the overall model is deployed on the clien…

Federated Learning Image Segmentation

SplitFed-CL: A Split Federated Co-Learning Framework for Medical Image Segmentation with Inaccurate Labels

2026-05-11 · Zahra Hafezi Kafshgari, Hadi Hadizadeh, Parvaneh Saeedi arxiv

Split Federated Learning (SplitFed) combines federated and split learning to preserve privacy while reducing client-side computation. However, in medical image segmentation, heterogeneous label quality across clients can…

Medical Image Segmentation Federated Learning

Enhancing Split Learning with Sharded and Blockchain-Enabled SplitFed Approaches

2025-09-29 · Amirreza Sokhankhosh, Khalid Hassan, Sara Rouhani arxiv

Collaborative and distributed learning techniques, such as Federated Learning (FL) and Split Learning (SL), hold significant promise for leveraging sensitive data in privacy-critical domains. However, FL and SL suffer fr…

Federated Learning

SplitFedZip: Learned Compression for Data Transfer Reduction in Split-Federated Learning

2024-12-18 · Chamani Shiranthika, Hadi Hadizadeh, Parvaneh Saeedi, Ivan V. Bajić

Federated Learning (FL) enables multiple clients to train a collaborative model without sharing their local data. Split Learning (SL) allows a model to be trained in a split manner across different locations. Split-Feder…

Federated Learning Image Segmentation Medical Image Segmentation Semantic Segmentation