Metraipolis › archive › dc_890d4e2aa58a

RGDM: Robust Graph Diffusion Model — arXiv:2611.04146

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04146
License (as archived)
CC0-1.0
Archived
2026-11-04T21:51:28.981Z
SHA-256 of the archived text
97616aca44f9567bb24d200fc5ea57b4a230b93cb1ca4700c2062d14a211df72
Stable URL of this page
https://metraipolis.com/documento/dc_890d4e2aa58a

How to cite

RGDM: Robust Graph Diffusion Model — arXiv:2611.04146 — arXiv (en), https://arxiv.org/abs/2611.04146 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_890d4e2aa58a (Metraipolis archive dc_890d4e2aa58a, sha256 97616aca44f9567bb24d200fc5ea57b4a230b93cb1ca4700c2062d14a211df72)
BibTeX
@misc{dc890d4e2aa58a,
  title = {RGDM: Robust Graph Diffusion Model — arXiv:2611.04146},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04146},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_890d4e2aa58a; sha256 97616aca44f9567bb24d200fc5ea57b4a230b93cb1ca4700c2062d14a211df72},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04146. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion models represent a powerful class of generative models known for their solid theoretical foundations and remarkable performance across diverse tasks and domains. Existing node level diffusion methods synthesize nodes and edges within a graph, but are not designed to learn a robust generator from adversarially corrupted graphs. In this study, we introduce the Robust Graph Diffusion Model (RGDM), designed to generate labeled synthetic graph structures consisting of nodes and edges that integrate seamlessly into a given graph. The RGDM consists of a Robust Graph Autoencoder (RGAE) and a Latent Diffusion Model (LDM). Leveraging an edge selection mechanism and an innovative low-rank regularization on the latent feature, the RGDM produces clean and high-quality synthetic graph structures, even when trained on graphs subject to adversarial attacks. Comprehensive experimental evaluations reveal that Graph Neural Networks (GNNs) trained on the augmented graph, which is formed by merging the original attacked graph with the synthetic graph structures, exhibit significantly improved robustness against various graph adversarial attacks in the context of semi-supervised node classification. The code of the RGDM is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.04146 — 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 2026-11-04T21:38:49.703Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).