Optimizing Split Points for Error-Resilient SplitFed Learning

2024/05/29 by Chamani Shiranthika, Shiranthika, Chamani, Parvaneh Saeedi +3 · 1 citation
Computer Science · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning and ELM

paper · pdf · doi:10.48550/arxiv.2405.19453

openalex publication_date 2024/05/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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 the computational burden on individual clients in FL and parallelize SL while maintaining privacy. This study investigates the resilience of SplitFed to packet loss at model split points. It explores various parameter aggregation strategies of SplitFed by examining the impact of splitting the model at different points-either shallow split or deep split-on the final global model performance. The experiments, conducted on a human embryo image segmentation task, reveal a statistically significant advantage of a deeper split point.

Cited by

• A New Pathway to Integrated Learning and Communication (ILAC): Large AI Model and Hyperdimensional Computing for Communication

Related

• SplitFed resilience to packet loss: Where to split, that is the question
• SplitFedZip: Learned Compression for Data Transfer Reduction in Split-Federated Learning
• Splitfed learning without client-side synchronization: Analyzing client-side split network portion size to overall performance
• SplitFed: When Federated Learning Meets Split Learning
• Quality-Adaptive Split-Federated Learning for Segmenting Medical Images with Inaccurate Annotations