Metraipolis › archive › dc_7390aa61a442

Message-passing graph persistence — arXiv:2611.06801

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06801
License (as archived)
CC0-1.0
Archived
2026-11-05T18:18:09.638Z
SHA-256 of the archived text
717538ddf7e31335e4f81f20945dba1568fa56961fbe9d2ce69ad6011857a4fe
Stable URL of this page
https://metraipolis.com/documento/dc_7390aa61a442

How to cite

Message-passing graph persistence — arXiv:2611.06801 — arXiv (en), https://arxiv.org/abs/2611.06801 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7390aa61a442 (Metraipolis archive dc_7390aa61a442, sha256 717538ddf7e31335e4f81f20945dba1568fa56961fbe9d2ce69ad6011857a4fe)
BibTeX
@misc{dc7390aa61a442,
  title = {Message-passing graph persistence — arXiv:2611.06801},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06801},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7390aa61a442; sha256 717538ddf7e31335e4f81f20945dba1568fa56961fbe9d2ce69ad6011857a4fe},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06801. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Message-passing graph neural networks (GNNs) are limited in expressive power by the one-dimensional Weisfeiler-Leman test. Persistent homology (PH) provides topological descriptors that can complement GNN representations, but existing approaches typically compute persistence separately from the representation learning process. In this paper, we introduce Message-Passing Graph Persistence (MGP), a family of topological descriptors that incorporates message passing into graph filtrations. At each filtration step, node embeddings are updated using the current subgraph and associated with persistence events. These embeddings also determine the representatives of connected components during persistence computation. We prove that MGP is invariant under graph isomorphism and that it is strictly more expressive than the PH-based descriptors it extends. We evaluate MGP on an expressivity benchmark and on several graph classification and regression datasets. Experiments show that MGP outperforms other PH-based descriptors on most of these datasets.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.06801 — 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 2026-11-05T18:12:49.069Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).