Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization

Tianshi Che, Ji Liu, Yang Zhou, Jiaxiang Ren, Jiwen Zhou, Victor Sheng, Huaiyu Dai, Dejing Dou


Abstract
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.
Anthology ID:
2023.emnlp-main.488
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7871–7888
Language:
URL:
https://aclanthology.org/2023.emnlp-main.488
DOI:
10.18653/v1/2023.emnlp-main.488
Bibkey:
Cite (ACL):
Tianshi Che, Ji Liu, Yang Zhou, Jiaxiang Ren, Jiwen Zhou, Victor Sheng, Huaiyu Dai, and Dejing Dou. 2023. Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7871–7888, Singapore. Association for Computational Linguistics.
Cite (Informal):
Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization (Che et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.488.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.488.mp4