English

Differentially Private Learning Needs Better Model Initialization and Self-Distillation

Machine Learning 2024-10-24 v1 Artificial Intelligence Computation and Language Cryptography and Security

Abstract

Differentially private SGD (DPSGD) enables privacy-preserving training of language models, but often reduces utility, diversity, and linguistic quality. We introduce DPRefine, a three-phase method that initializes a model using data synthesis from a small pre-trained LM with rigorous filtering, applies DP finetuning on private data, and performs self-distillation to refine outputs. This approach significantly outperforms vanilla DPSGD, with AlpacaEval preferring DPRefine's generations in 78.4% of cases across all datasets. Our analysis reveals that DPRefine reduces linguistic errors in generated text by 84.0%, mitigating grammar and spelling errors, commonly associated with DPSGD. It also reduces inconsistencies of non-private models, such as hallucinated details and misattributed quotes. We find that small models like GPT-2 can be effective for initialization and distillation, highlighting their potential in enabling scalable and efficient deployment of privacy-preserving language.

Keywords

Cite

@article{arxiv.2410.17566,
  title  = {Differentially Private Learning Needs Better Model Initialization and Self-Distillation},
  author = {Ivoline C. Ngong and Joseph P. Near and Niloofar Mireshghallah},
  journal= {arXiv preprint arXiv:2410.17566},
  year   = {2024}
}

Comments

18 pages

R2 v1 2026-06-28T19:32:25.484Z