Metraipolis › archive › dc_274ca45fba85

Graph Data Augmentation via Contrastive Generator Inversion ($\texttt{DCBA}$) — arXiv:2610.05653

Source: arXiv
Original: https://arxiv.org/abs/2610.05653
License (as archived): CC0-1.0
Archived: 2026-10-06T05:29:40.252Z
SHA-256 of the archived text: 11683ef02bedbc243694223b2d02ddb2be2fe906a2f98b883bb1aba5f3630173
Stable URL of this page: https://metraipolis.com/documento/dc_274ca45fba85

How to cite

Graph Data Augmentation via Contrastive Generator Inversion ($\texttt{DCBA}$) — arXiv:2610.05653 — arXiv, https://arxiv.org/abs/2610.05653 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_274ca45fba85 (Metraipolis archive dc_274ca45fba85, sha256 11683ef02bedbc243694223b2d02ddb2be2fe906a2f98b883bb1aba5f3630173)

BibTeX

@misc{dc274ca45fba85,
  title = {Graph Data Augmentation via Contrastive Generator Inversion ($textttDCBA$) — arXiv:2610.05653},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05653},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_274ca45fba85; sha256 11683ef02bedbc243694223b2d02ddb2be2fe906a2f98b883bb1aba5f3630173},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05653. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: governance digitale e beni comuni (elenco arXiv cs.SI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Social and Information Networks (cs.SI).
Pagina del lavoro: https://arxiv.org/abs/2610.05653 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:26:20.293Z dalla pagina https://arxiv.org/list/cs.SI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).