Metraipolis › archive › dc_24d88696752c

A Network Science Perspective on Evaluating Deep Graph Generative Models — arXiv:2609.01015

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01015
License (as archived)
CC0-1.0
Archived
2026-10-17T06:33:51.365Z
SHA-256 of the archived text
e33e23122dd2addc14f8250f048e663bb36304b4013f4ff85f962bd19aa77dce
Stable URL of this page
https://metraipolis.com/documento/dc_24d88696752c

How to cite

A Network Science Perspective on Evaluating Deep Graph Generative Models — arXiv:2609.01015 — arXiv (en), https://arxiv.org/abs/2609.01015 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_24d88696752c (Metraipolis archive dc_24d88696752c, sha256 e33e23122dd2addc14f8250f048e663bb36304b4013f4ff85f962bd19aa77dce)
BibTeX
@misc{dc24d88696752c,
  title = {A Network Science Perspective on Evaluating Deep Graph Generative Models — arXiv:2609.01015},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01015},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_24d88696752c; sha256 e33e23122dd2addc14f8250f048e663bb36304b4013f4ff85f962bd19aa77dce},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01015. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Traditional network models from network science, such as the Erdos-Renyi and configuration models, generate random networks that reproduce few selected topological properties observed in real-world networks. Deep graph generative models emerge as a data-driven approach, leveraging deep neural network architectures to learn complex structural distributions directly from real-world networks to generate more realistic synthetic networks. Because real social contact networks cannot be shared due to privacy risks, synthetic networks serve as an alternative for developing and evaluating epidemic mitigation strategies. In this work, we evaluate deep graph generative models as well as the configuration from a network science perspective by assessing both the topological similarity between generated and real-world networks and their utility in identifying effective node immunization strategies to sup- press epidemic/misinformation spreading. It is found that two deep graph generative models produce synthetic networks that closely resemble the structural properties of real-world networks, enabling them to identify effective immunization strategies.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Social and Information Networks (cs.SI) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.01015 — 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 2026-10-17T06:15:12.849Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).