Sparsity-Preserving Differentially Private Training of Large Embedding Models
Badih Ghazi · Yangsibo Huang · Pritish Kamath · Ravi Kumar · Pasin Manurangsi · Amer Sinha · Chiyuan Zhang
Great Hall & Hall B1+B2 (level 1) #1614
Abstract: 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.
Chat is not available.