Metraipolis › archive › dc_89ded2bd7044

GeoGAE: Scalable Graph-Level Autoencoding via Hyperball Cloud Representations — arXiv:2609.35527

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.35527
License (as archived): CC0-1.0
Archived: 2026-10-07T22:39:12.909Z
SHA-256 of the archived text: 15e25df7045d57cacdc7004da29b6b9a58fa992b9f8df1c534b431f93e848c3f
Stable URL of this page: https://metraipolis.com/documento/dc_89ded2bd7044

How to cite

GeoGAE: Scalable Graph-Level Autoencoding via Hyperball Cloud Representations — arXiv:2609.35527 — arXiv (en), https://arxiv.org/abs/2609.35527 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89ded2bd7044 (Metraipolis archive dc_89ded2bd7044, sha256 15e25df7045d57cacdc7004da29b6b9a58fa992b9f8df1c534b431f93e848c3f)

BibTeX

@misc{dc89ded2bd7044,
  title = {GeoGAE: Scalable Graph-Level Autoencoding via Hyperball Cloud Representations — arXiv:2609.35527},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35527},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89ded2bd7044; sha256 15e25df7045d57cacdc7004da29b6b9a58fa992b9f8df1c534b431f93e848c3f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35527. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Embedding structured objects into Euclidean spaces has enabled a wide range of successful machine learning applications. Such objects include words, documents, image patches, time series, and graph nodes. In contrast, embedding entire graphs remains a challenging problem. Existing methods either sustain the original order of the graph nodes or match the output nodes to the input ones, both of which create scalability issues. In this work, we propose a graph representation as a cloud of hyperballs, which allows us to define a specific, typically unique, node ordering. Based on this representation, we propose GeoGAE, an autoencoder, in which the Transformer encoder translates a hyperball cloud into a graph-level embedding, and the Transformer decoder translates the graph-level embedding back into the graph. This formulation enables the model to capture both the global graph structure and local relational patterns. We evaluate our method on multiple graph datasets, spanning various domains. The results demonstrate effectiveness of our method in encoding and reconstructing graphs from their embeddings.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.35527 — 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 2026-10-07T22:14:28.469Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).