Can Public Large Language Models Help Private Cross-device Federated Learning?

Boxin Wang, Yibo Zhang, Yuan Cao, Bo Li, Hugh McMahan, Sewoong Oh, Zheng Xu, Manzil Zaheer


Abstract
We study (differentially) private federated learning (FL) of language models. The language models in cross-device FL are relatively small, which can be trained with meaningful formal user-level differential privacy (DP) guarantees when massive parallelism in training is enabled by the participation of a moderate size of users. Recently, public data has been used to improve privacy-utility trade-offs for both large and small language models. In this work, we provide a systematic study of using large-scale public data and LLMs to help differentially private training of on-device FL models, and further improve the privacy-utility tradeoff by techniques of distillation. Moreover, we propose a novel distribution matching algorithm with theoretical grounding to sample public data close to private data distribution, which significantly improves the sample efficiency of (pre-)training on public data. The proposed method is efficient and effective for training private models by taking advantage of public data, especially for customized on-device architectures that do not have ready-touse pre-trained models.
Anthology ID:
2024.findings-naacl.59
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
934–949
Language:
URL:
https://aclanthology.org/2024.findings-naacl.59
DOI:
Bibkey:
Cite (ACL):
Boxin Wang, Yibo Zhang, Yuan Cao, Bo Li, Hugh McMahan, Sewoong Oh, Zheng Xu, and Manzil Zaheer. 2024. Can Public Large Language Models Help Private Cross-device Federated Learning?. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 934–949, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Can Public Large Language Models Help Private Cross-device Federated Learning? (Wang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.59.pdf
Copyright:
 2024.findings-naacl.59.copyright.pdf