We address the challenge of ensuring differential privacy (DP) guarantees in training deep retrieval systems. Training these systems often involves the use of contrastive-style losses, which are typically non-per-example decomposable, making them difficult to directly DP-train with since common techniques require per-example gradient. To address this issue, we propose an approach that prioritizes ensuring query privacy prior to training a deep retrieval system. Our method employs DP language models (LMs) to generate private synthetic queries representative of the original data. These synthetic queries can be used in downstream retrieval system training without compromising privacy. Our approach demonstrates a significant enhancement in retrieval quality compared to direct DP-training, all while maintaining query-level privacy guarantees. This work highlights the potential of harnessing LMs to overcome limitations in standard DP-training methods.

翻译：我们致力于解决在训练深度检索系统时确保差分隐私（DP）保证的挑战。此类系统的训练常涉及对比式损失函数，其通常不具备逐样本可分解性，而现有常见技术需要逐样本梯度，因此难以直接进行DP训练。为解决该问题，我们提出一种在训练深度检索系统之前优先确保查询隐私的方法。本方法利用差分隐私语言模型生成代表原始数据的私有合成查询，这些合成查询可在不牺牲隐私的前提下用于下游检索系统的训练。与直接DP训练相比，本方法在保持查询级隐私保证的同时，显著提升了检索质量。该工作凸显了利用语言模型克服标准DP训练方法局限性的潜力。