Metraipolis › archive › dc_3fe8bdaedc9c

G-NAC: Graph Neural Automata Clustering via Emergent Domain Formation — arXiv:2609.24823

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24823
License (as archived)
CC0-1.0
Archived
2026-10-09T07:07:56.710Z
SHA-256 of the archived text
b35101a4bf0dd7f6db27a3dbdaeebdf3a49f90411245465efcb70c3e9f384ce3
Stable URL of this page
https://metraipolis.com/documento/dc_3fe8bdaedc9c

How to cite

G-NAC: Graph Neural Automata Clustering via Emergent Domain Formation — arXiv:2609.24823 — arXiv (en), https://arxiv.org/abs/2609.24823 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3fe8bdaedc9c (Metraipolis archive dc_3fe8bdaedc9c, sha256 b35101a4bf0dd7f6db27a3dbdaeebdf3a49f90411245465efcb70c3e9f384ce3)
BibTeX
@misc{dc3fe8bdaedc9c,
  title = {G-NAC: Graph Neural Automata Clustering via Emergent Domain Formation — arXiv:2609.24823},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24823},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3fe8bdaedc9c; sha256 b35101a4bf0dd7f6db27a3dbdaeebdf3a49f90411245465efcb70c3e9f384ce3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24823. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce Graph Neural Automata Clustering (G-NAC), an unsupervised clustering method in which observations interact as cells on a fixed neighborhood graph. A shared recurrent graph-neural cellular rule evolves latent domain states through local interactions, which are converted into a rank-based spectral affinity for partitioning. Across 73 clustering tasks from 57 benchmark datasets, G-NAC achieved a mean adjusted Rand index (ARI) of 0.7951, comparable to Genie at 0.7941 and higher than the other evaluated baselines. Empirical training time and GPU memory scaled approximately linearly from 5,000 to 100,000 nodes. Learned transition rules also transferred from smaller source graphs to independent 100,000-node samples generated under matched conditions. These results demonstrate a recurrent graph-clustering formulation while identifying dependencies on graph quality, readout design, and source-target similarity.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Signal Processing (eess.SP).
Pagina del lavoro: https://arxiv.org/abs/2609.24823 — 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 2026-10-09T06:58:09.451Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).