Conference paper · 2023 · Open access

FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning

Yuanhao Xiong, Ruochen Wang, Minhao Cheng, Felix Yu, Cho‐Jui Hsieh

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 16323–16332 · Published 1 June 2023 · DOI 10.1109/cvpr52729.2023.01566

Open PDFView at the publisherCite this paper

In brief

“FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning” is a 2023 conference paper by Yuanhao Xiong and 4 co-authors, published in IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings. OpenAlex counts 180 citations as of 21 November 2026, which puts it in the top 8% of works published in 2023 by citations. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
180
Most cited in
2024 (64)
Field-weighted impact
11.11
References
58
Authors
5

Abstract

Federated learning (FL) has recently attracted increasing attention from academia and industry, with the ultimate goal of achieving collaborative training under privacy and communication constraints. Existing iterative model averaging based FL algorithms require a large number of communication rounds to obtain a well-performed model due to extremely unbalanced and non-i.i.d data partitioning among different clients. Thus, we propose FedDM to build the global training objective from multiple local surrogate functions, which enables the server to gain a more global view of the loss landscape. In detail, we construct synthetic sets of data on each client to locally match the loss landscape from original data through distribution matching. FedDM reduces communication rounds and improves model quality by transmitting more informative and smaller synthesized data compared with unwieldy model weights. We conduct extensive experiments on three image classification datasets, and show that our method outperforms other FL counterparts in terms of efficiency and model performance given a limited number of communication rounds. Moreover, we demonstrate that FedDM can be adapted to preserve differential privacy with Gaussian mechanism and train a better model under the same privacy budget.

Cite this paper

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

APA 7

Xiong, Y., Wang, R., Cheng, M., Yu, F., & Hsieh, C. (2023). FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 16323–16332. https://doi.org/10.1109/cvpr52729.2023.01566

MLA 9

Xiong, Yuanhao, et al. “FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 2023, pp. 16323–16332. https://doi.org/10.1109/cvpr52729.2023.01566.

Chicago

Xiong, Yuanhao, Ruochen Wang, Minhao Cheng, Felix Yu, and Cho‐Jui Hsieh. 2023. “FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings: 16323–16332. https://doi.org/10.1109/cvpr52729.2023.01566.

Harvard

Xiong, Y. et al. (2023) ‘FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning’, IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 16323–16332. doi:10.1109/cvpr52729.2023.01566.

IEEE

Y. Xiong, R. Wang, M. Cheng, F. Yu, and C. Hsieh, “FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 16323–16332, 2023, doi: 10.1109/cvpr52729.2023.01566.

BibTeX

@inproceedings{xiong2023feddm,
  title     = {{FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning}},
  author    = {Xiong, Yuanhao and Wang, Ruochen and Cheng, Minhao and Yu, Felix and Hsieh, Cho‐Jui},
  booktitle = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings},
  year      = {2023},
  pages     = {16323--16332},
  doi       = {10.1109/cvpr52729.2023.01566},
  url       = {https://doi.org/10.1109/cvpr52729.2023.01566}
}

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

Citations by year

YearCitationsShare of the best year
202222
20232020
20246464
20254646
20264848

Its field-weighted citation impact is 11.11: it has been cited 11.11 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

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

  • federated learning
  • distribution matching
  • communication efficiency
  • non-IID data
  • loss landscape
  • synthetic data
  • surrogate functions
  • model averaging

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?

Xiong, Y., Wang, R., Cheng, M., Yu, F., & Hsieh, C. (2023). FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 16323–16332. https://doi.org/10.1109/cvpr52729.2023.01566

How many times has this paper been cited?

180 times, according to OpenAlex on 21 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?

Yuanhao Xiong, Ruochen Wang, Minhao Cheng, Felix Yu, Cho‐Jui Hsieh.

What is the DOI of this paper?

10.1109/cvpr52729.2023.01566, permanently at https://doi.org/10.1109/cvpr52729.2023.01566. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 21 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.