AI RESEARCH
GAPSL: A Gradient-Aligned Parallel Split Learning on Heterogeneous Data
arXiv CS.LG
•
ArXi:2603.18540v1 Announce Type: new The increasing complexity of neural networks poses significant challenges for cratizing FL on resource?constrained client devices. Parallel split learning (PSL) has emerged as a promising solution by offloading substantial computing workload to a server via model partitioning, shrinking client-side computing load, and eliminating the client-side model aggregation for reduced communication and deployment costs. Since PSL is aggregation-free, it suffers from severe.