Differentially Private Fine-tuning of Language Models

Understand

We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-scale pre-trained language models, which achieve the state-of-the-art privacy versus utility tradeoffs on many standard NLP tasks.

• We propose a meta-framework for this problem, inspired by the recent success of highly parameter-efficient methods for fine-tuning.
• Our experiments show that differentially private adaptations of these approaches outperform previous private algorithms in three important dimensions: utility, privacy, and the computational and memory cost of private training.
• On many commonly studied datasets, the utility of private models approaches that of non-private models.