Preprint · 2025 · Open access

RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models

Jiang, Tanqiu, Changjiang Li, Fenglong Ma, Ting Wang

arXiv (Cornell University) · Published 18 February 2025 · DOI 10.48550/arxiv.2502.12794

Open PDFView at the publisherCite this paper

In brief

“RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models” is a 2025 preprint by Jiang, Tanqiu and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 3 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
3
Most cited in
2026 (2)
References
25
Authors
4

Abstract

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

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Tanqiu, J., Li, C., Ma, F., & Wang, T. (2025). RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2502.12794

MLA 9

Tanqiu, Jiang,, et al. “RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2502.12794.

Chicago

Tanqiu, Jiang,, Changjiang Li, Fenglong Ma, and Ting Wang. 2025. “RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2502.12794.

Harvard

Tanqiu, J. et al. (2025) ‘RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models’, arXiv (Cornell University). doi:10.48550/arxiv.2502.12794.

IEEE

J. Tanqiu, C. Li, F. Ma, and T. Wang, “RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2502.12794.

BibTeX

@misc{tanqiu2025rapid,
  title     = {{RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models}},
  author    = {Tanqiu, Jiang, and Li, Changjiang and Ma, Fenglong and Wang, Ting},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2502.12794},
  url       = {https://doi.org/10.48550/arxiv.2502.12794}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • retrieval-augmented generation
  • differential privacy
  • training cost reduction
  • memory usage
  • inference cost

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Tanqiu, J., Li, C., Ma, F., & Wang, T. (2025). RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2502.12794

How many times has this paper been cited?

3 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Jiang, Tanqiu, Changjiang Li, Fenglong Ma, Ting Wang.

What is the DOI of this paper?

10.48550/arxiv.2502.12794, permanently at https://doi.org/10.48550/arxiv.2502.12794. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.