Abstract
Graphs provide a natural representation of many complex systems, ranging from social platforms to ecosystems. However, the development of graph-based machine learning methods is often constrained by the limited availability of large and diverse graph datasets. In this paper, we introduce $\texttt{DCBA}$, a model-based approach to graph data augmentation that infers the configuration of a synthetic graph generator from an observed network. We instantiate the proposed framework using the $\texttt{ABCD}$ generator, which produces scale-free networks with community structure. Our model learns a joint representation of graphs and generator parametrisations using a multi-positive contrastive objective with soft negative weighting. The learned representation enables the prediction of an $\texttt{ABCD}$ configuration whose stochastic realisations preserve the macrostructural properties encoded by the generator. Experiments show that $\texttt{DCBA}$ recovers generator parameters more accurately and robustly than an algorithmic inverse-modelling baseline. Its downstream utility is further demonstrated in community detection, where inferred configurations used to fine-tune $\texttt{PRoCD}$ improve AMI on average by $161\%$ on synthetic and $273\%$ on real-world networks.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Stolarski, M., Czuba, M., Kraiński, Ł., Musial, K., Prałat, P., Kamiński, B., & Bródka, P. (2026). Graph Data Augmentation via Contrastive Generator Inversion ($\texttt{DCBA}$). https://omanscience.com/en/articles/graph-data-augmentation-via-contrastive-generator-inversion-texttt-dcba
MLA 9
Stolarski, Mateusz, et al. "Graph Data Augmentation via Contrastive Generator Inversion ($\texttt{DCBA}$)." https://omanscience.com/en/articles/graph-data-augmentation-via-contrastive-generator-inversion-texttt-dcba.
Chicago (author–date)
Stolarski, Mateusz, Michał Czuba, Łukasz Kraiński, Katarzyna Musial, Paweł Prałat, Bogumił Kamiński, and Piotr Bródka. 2026. "Graph Data Augmentation via Contrastive Generator Inversion ($\texttt{DCBA}$)." https://omanscience.com/en/articles/graph-data-augmentation-via-contrastive-generator-inversion-texttt-dcba.
Harvard
Stolarski, M., Czuba, M., Kraiński, Ł., Musial, K., Prałat, P., Kamiński, B. and Bródka, P. (2026) 'Graph Data Augmentation via Contrastive Generator Inversion ($\texttt{DCBA}$)', Available at: https://omanscience.com/en/articles/graph-data-augmentation-via-contrastive-generator-inversion-texttt-dcba.
Vancouver
Stolarski M, Czuba M, Kraiński Ł, Musial K, Prałat P, Kamiński B, et al. Graph Data Augmentation via Contrastive Generator Inversion ($\texttt{DCBA}$). https://omanscience.com/en/articles/graph-data-augmentation-via-contrastive-generator-inversion-texttt-dcba
IEEE
M. Stolarski, M. Czuba, Ł. Kraiński, K. Musial, P. Prałat, B. Kamiński, and P. Bródka, "Graph Data Augmentation via Contrastive Generator Inversion ($\texttt{DCBA}$)," https://omanscience.com/en/articles/graph-data-augmentation-via-contrastive-generator-inversion-texttt-dcba.