Private Synthetic Graph Generation and Fused Gromov-Wasserstein Distance

Leoni Carla Wirth, Gholamali Aminian, Gesine Reinert
Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, PMLR 300:1774-1782, 2026.

Abstract

Networks are popular representations of complex data. In particular, differentially private synthetic networks are much in demand. Here, instead of starting from a network, we start with the complex data set itself and construct both a network representation and a corresponding synthetic network generator. We build a network model directly based on the underlying complex system data, capturing its structure and attributes. Using a random connection model, we devise an effective algorithmic approach for generating attributed synthetic networks which is $\epsilon$-differentially private at the vertex level, while preserving utility. We provide theoretical guarantees for the accuracy of the private synthetic networks using the fused Gromov-Wasserstein distance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v300-wirth26a, title = { Private Synthetic Graph Generation and Fused Gromov-Wasserstein Distance }, author = {Wirth, Leoni Carla and Aminian, Gholamali and Reinert, Gesine}, booktitle = {Proceedings of The 29th International Conference on Artificial Intelligence and Statistics}, pages = {1774--1782}, year = {2026}, editor = {Khan, Emtiyaz and Li, Yingzhen and Solin, Arno and Ramdas, Aaditya}, volume = {300}, series = {Proceedings of Machine Learning Research}, month = {02--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v300/main/assets/wirth26a/wirth26a.pdf}, url = {https://proceedings.mlr.press/v300/wirth26a.html}, abstract = { Networks are popular representations of complex data. In particular, differentially private synthetic networks are much in demand. Here, instead of starting from a network, we start with the complex data set itself and construct both a network representation and a corresponding synthetic network generator. We build a network model directly based on the underlying complex system data, capturing its structure and attributes. Using a random connection model, we devise an effective algorithmic approach for generating attributed synthetic networks which is $\epsilon$-differentially private at the vertex level, while preserving utility. We provide theoretical guarantees for the accuracy of the private synthetic networks using the fused Gromov-Wasserstein distance. } }
Endnote
%0 Conference Paper %T Private Synthetic Graph Generation and Fused Gromov-Wasserstein Distance %A Leoni Carla Wirth %A Gholamali Aminian %A Gesine Reinert %B Proceedings of The 29th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2026 %E Emtiyaz Khan %E Yingzhen Li %E Arno Solin %E Aaditya Ramdas %F pmlr-v300-wirth26a %I PMLR %P 1774--1782 %U https://proceedings.mlr.press/v300/wirth26a.html %V 300 %X Networks are popular representations of complex data. In particular, differentially private synthetic networks are much in demand. Here, instead of starting from a network, we start with the complex data set itself and construct both a network representation and a corresponding synthetic network generator. We build a network model directly based on the underlying complex system data, capturing its structure and attributes. Using a random connection model, we devise an effective algorithmic approach for generating attributed synthetic networks which is $\epsilon$-differentially private at the vertex level, while preserving utility. We provide theoretical guarantees for the accuracy of the private synthetic networks using the fused Gromov-Wasserstein distance.
APA
Wirth, L.C., Aminian, G. & Reinert, G.. (2026). Private Synthetic Graph Generation and Fused Gromov-Wasserstein Distance . Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 300:1774-1782 Available from https://proceedings.mlr.press/v300/wirth26a.html.

Related Material