FedBiOT: a solution for federated large language model fine-tuning with intellectual property protection

Feijie Wu, Zitao Li, Yaliang Li, Bolin Ding, Jing Gao

Primary Area: general machine learning (i.e., none of the above)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Federated Learning, Large Language Model

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: Due to data and information privacy concerns, data owners are not willing to share the data with others, but each of them may not have sufficient data to fine-tune a satisfactory large language model (LLM) individually. Parallelly, the LLM owners may not be willing to disclose the LLMs' details, including their architectures and parameters. Therefore, this leads to the challenge of fine-tuning an LLM on a federated learning task where the clients with task-specific data cannot obtain the complete LLM. To solve the challenge, this paper introduces FedBiOT, a method that guarantees the clients' data privacy and avoids the disclosure of an LLM. Specifically, we formulate and solve a bi-level optimization problem to ensure that the emulator distilled on the public dataset by the LLM owner can help the adaptors' local fine-tuning on clients' private datasets, regardless of the distribution drift between those datasets. Different clients' adapters are synchronized in a federated learning style, and the full model composed with the final derived adapter can achieve better performance on downstream tasks. We conduct extensive experiments on LLaMA-7B training for various federated learning tasks and witness significant improvements over existing baselines.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 6725