AI RESEARCH
FedMomentum: Preserving LoRA Training Momentum in Federated Fine-Tuning
arXiv CS.LG
•
ArXi:2603.08014v1 Announce Type: new Federated fine-tuning of large language models (LLMs) with low-rank adaptation (LoRA) offers a communication-efficient and privacy-preserving solution for task-specific adaptation. Naive aggregation of LoRA modules