用公开数据辅助训练私密扩散模型，提升生成质量并降低资源开销。
RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models
- 利用公开数据构建轨迹知识库，检索相似路径替代私有数据早期采样
- 在相同隐私保护下，生成质量显著优于现有方法，内存与推理成本大幅降低
- 适合需要高隐私保障且资源受限的生成模型应用，如医疗图像生成
差分隐私扩散模型（DPDM）在保持生成能力的同时，为敏感数据提供差分隐私保护。然而，现有训练方法普遍存在性能损失大、内存占用高、推理成本昂贵等问题，限制了实际应用。为此，本文提出RAPID：一种将检索增强生成（RAG）引入差分隐私扩散模型训练的新方法。具体而言，RAPID利用公开数据构建样本轨迹知识库；训练私有数据时，将早期采样步骤作为查询，从知识库中检索相似轨迹作为替代，并仅对后期采样步骤进行差分隐私训练。在基准数据集和模型上的广泛评估表明，在相同隐私保证下，RAPID在生成质量、内存占用和推理成本上均显著优于当前最优方法，表明检索增强的私密训练是未来隐私保护生成模型的重要方向。代码已开源：https://github.com/TanqiuJiang/RAPID
原文摘要 · Abstract (English)
Differentially private diffusion models (DPDMs) harness the remarkable generative capabilities of diffusion models while enforcing differential privacy (DP) for sensitive data. However, existing DPDM training approaches often suffer from significant utility loss, large memory footprint, and expensive inference cost, impeding their practical uses. To overcome such limitations, we present RAPID: Retrieval Augmented PrIvate Diffusion model, a novel approach that integrates retrieval augmented generation (RAG) into DPDM training. Specifically, RAPID leverages available public data to build a knowledge base of sample trajectories; when training the diffusion model on private data, RAPID computes the early sampling steps as queries, retrieves similar trajectories from the knowledge base as surrogates, and focuses on training the later sampling steps in a differentially private manner. Extensive evaluation using benchmark datasets and models demonstrates that, with the same privacy guarantee, RAPID significantly outperforms state-of-the-art approaches by large margins in generative quality, memory footprint, and inference cost, suggesting that retrieval-augmented DP training represents a promising direction for developing future privacy-preserving generative models. The code is available at: https://github.com/TanqiuJiang/RAPID
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。