Can Public Large Language Models Help Private Cross-device Federated Learning?
Keywords: differential privacy, federated learning, on device, large language models
TL;DR: We propose to leverage LLMs to aid public training of on-device LMs via distribution matching to sample public data close to private data distribution, which further improves the effectiveness and efﬁciency of public training.
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-to-use pre-trained models.
Submission Number: 13