Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes
Zhen Qin, Daoyuan Chen, Bingchen Qian, Bolin Ding, Yaliang Li, Shuiguang Deng
TL;DR
This paper tackles the challenge of federated full-parameter tuning for billion-sized LLMs by introducing FedKSeed, a zeroth-order FL approach that communicates only a fixed set of random seeds and scalar gradients, achieving per-round transmission under 18 KB. Building on this, FedKSeed-Pro adds non-uniform seed sampling to prioritize perturbations with larger impact on accuracy, further reducing seed requirements while improving performance. The method maintains convergence comparable to FedZO under standard assumptions and demonstrates average Rouge-L gains of about 7.26% over practical baselines, alongside roughly a thousand-fold reduction in communication. The results show FedKSeed and FedKSeed-Pro enable practical full-parameter federated tuning on devices, with strong robustness across model sizes, datasets, and federated settings, opening pathways for decentralized, privacy-preserving large-model adaptation.
Abstract
Pre-trained large language models (LLMs) need fine-tuning to improve their responsiveness to natural language instructions. Federated learning offers a way to fine-tune LLMs using the abundant data on end devices without compromising data privacy. Most existing federated fine-tuning methods for LLMs rely on parameter-efficient fine-tuning techniques, which may not reach the performance height possible with full-parameter tuning. However, federated full-parameter tuning of LLMs is a non-trivial problem due to the immense communication cost. This work introduces FedKSeed that employs zeroth-order optimization with a finite set of random seeds. It significantly reduces transmission requirements between the server and clients to just a few random seeds and scalar gradients, amounting to only a few thousand bytes, making federated full-parameter tuning of billion-sized LLMs possible on devices. Building on it, we develop a strategy enabling probability-differentiated seed sampling, prioritizing perturbations with greater impact on model accuracy. Experiments across six scenarios with various LLMs, datasets and data partitions demonstrate that our approach outperforms existing federated LLM fine-tuning methods in both communication efficiency and new task generalization.