Federated learning (FL) is a promising paradigm to enable collaborative model training with decentralized data. However, the training process of Large Language Models (LLMs) generally incurs the update of significant parameters, which limits the applicability of FL techniques to tackle the LLMs in real scenarios. Prompt tuning can significantly reduce the number of parameters to update, but it either incurs performance degradation or low training efficiency. The straightforward utilization of prompt tuning in the FL often raises non-trivial communication costs and dramatically degrades performance. In addition, the decentralized data is generally non-Independent and Identically Distributed (non-IID), which brings client drift problems and thus poor performance. This paper proposes a Parameter-efficient prompt Tuning approach with Adaptive Optimization, i.e., FedPepTAO, to enable efficient and effective FL of LLMs. First, an efficient partial prompt tuning approach is proposed to improve performance and efficiency simultaneously. Second, a novel adaptive optimization method is developed to address the client drift problems on both the device and server sides to enhance performance further. Extensive experiments based on 10 datasets demonstrate the superb performance (up to 60.8\% in terms of accuracy) and efficiency (up to 97.59\% in terms of training time) of FedPepTAO compared with 9 baseline approaches. Our code is available at https://github.com/llm-eff/FedPepTAO.

翻译：联邦学习（FL）是一种能够利用分散数据实现协作模型训练的前景广阔范式。然而，大语言模型（LLM）的训练通常涉及大量参数的更新，这限制了FL技术在真实场景中处理LLM的适用性。提示调优可显著减少需更新的参数数量，但其要么导致性能下降，要么训练效率低下。在FL中直接应用提示调优往往会引发非平凡通信成本并显著降低性能。此外，分散数据通常呈现非独立同分布（non-IID）特性，导致客户端漂移问题进而影响性能。本文提出一种参数高效提示调优与自适应优化方法——FedPepTAO，以实现高效且有效的LLM联邦学习。首先，提出一种高效局部提示调优方法，同步提升性能与效率；其次，开发一种新型自适应优化方法，分别从设备端与服务器端解决客户端漂移问题以进一步增强性能。基于10个数据集的广泛实验表明，与9种基准方法相比，FedPepTAO在准确率上最高提升60.8%，在训练时间上最高降低97.59%的效率优势。我们的代码可在https://github.com/llm-eff/FedPepTAO获取。