Hugh McMahan
2024
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
Findings of the Association for Computational Linguistics: NAACL 2024
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.
Search
Co-authors
- Boxin Wang 1
- Yibo Zhang 1
- Yuan Cao 1
- Bo Li 1
- Sewoong Oh 1
- show all...