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

arXiv:2305.12132v2 Announce Type: replace
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 …

abstract arxiv cs.lg differential differential privacy federated learning language language models large language large language models massive privacy public small study training type