Sparsity-Preserving Differentially Private Training of Large Embedding Models

Part of Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Main Conference Track

Bibtex Paper Supplemental


Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang


As the use of large embedding models in recommendation systems and language applications increases, concerns over user data privacy have also risen. DP-SGD, a training algorithm that combines differential privacy with stochastic gradient descent, has been the workhorse in protecting user privacy without compromising model accuracy by much. However, applying DP-SGD naively to embedding models can destroy gradient sparsity, leading to reduced training efficiency. To address this issue, we present two new algorithms, DP-FEST and DP-AdaFEST, that preserve gradient sparsity during the private training of large embedding models. Our algorithms achieve substantial reductions ($10^6 \times$) in gradient size, while maintaining comparable levels of accuracy, on benchmark real-world datasets.