Metraipolis › archive › dc_406f6c14aa52

Topology-induced Operators Reveal Complementary Graph Representations without Training — arXiv:2609.08152

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.08152
License (as archived)
CC0-1.0
Archived
2026-10-16T13:39:45.024Z
SHA-256 of the archived text
cff792b9b0d5b2f94f3dc647cd6cc1dfbe56e6355576169760fda55fb4a2de00
Stable URL of this page
https://metraipolis.com/documento/dc_406f6c14aa52

How to cite

Topology-induced Operators Reveal Complementary Graph Representations without Training — arXiv:2609.08152 — arXiv (en), https://arxiv.org/abs/2609.08152 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_406f6c14aa52 (Metraipolis archive dc_406f6c14aa52, sha256 cff792b9b0d5b2f94f3dc647cd6cc1dfbe56e6355576169760fda55fb4a2de00)
BibTeX
@misc{dc406f6c14aa52,
  title = {Topology-induced Operators Reveal Complementary Graph Representations without Training — arXiv:2609.08152},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08152},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_406f6c14aa52; sha256 cff792b9b0d5b2f94f3dc647cd6cc1dfbe56e6355576169760fda55fb4a2de00},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08152. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Graph representation learning has largely focused on designing increasingly sophisticated models to transform graph topology into vector representations, or embeddings. However, the extent to which embedding quality depends on model learning, rather than on the underlying topological transformations, remains unclear. Here, we show that informative embeddings can be derived without complicated model design and gradient-based training. Propagating random features through implicit hierarchical structures induced by random walks and anonymous walks yields embeddings that capture node proximity and structural role, respectively. These two training-free embeddings preserve complementary aspects of graph organization and perform competitively with classic and recent methods across various node-, edge-, and graph-level tasks. They often require substantially less computation, resulting in a favorable quality-efficiency trade-off. Combining the two types of embeddings further improves inference quality of some tasks compared with using either embedding type alone. Our results suggest that informative graph embeddings can arise from carefully chosen topological transformations before any learning operation is applied.

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-09-09 in cs.SI).
Categorie arXiv: Machine Learning (cs.LG) ; Social and Information Networks (cs.SI).
Pagina del lavoro: https://arxiv.org/abs/2609.08152 — 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 2026-10-16T13:07:42.344Z dalla pagina https://arxiv.org/catchup/cs.SI/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).