Metraipolis › archive › dc_3645493b116a

Learning the Graph and the Embedding Together: Classifier-Independent Rewiring for Heterophilic Node Classification — arXiv:2609.32613

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32613
License (as archived)
CC0-1.0
Archived
2026-10-07T22:36:43.036Z
SHA-256 of the archived text
de9a3881e77c821fe50568b442184519ad500d93e33675a0dc93d466b22b9fa8
Stable URL of this page
https://metraipolis.com/documento/dc_3645493b116a

How to cite

Learning the Graph and the Embedding Together: Classifier-Independent Rewiring for Heterophilic Node Classification — arXiv:2609.32613 — arXiv (en), https://arxiv.org/abs/2609.32613 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3645493b116a (Metraipolis archive dc_3645493b116a, sha256 de9a3881e77c821fe50568b442184519ad500d93e33675a0dc93d466b22b9fa8)
BibTeX
@misc{dc3645493b116a,
  title = {Learning the Graph and the Embedding Together: Classifier-Independent Rewiring for Heterophilic Node Classification — arXiv:2609.32613},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32613},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3645493b116a; sha256 de9a3881e77c821fe50568b442184519ad500d93e33675a0dc93d466b22b9fa8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32613. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Graph neural networks lose much of their advantage on heterophilic graphs, where connected nodes often carry different labels. Graph rewiring is a popular remedy, but rewiring methods are usually evaluated with a single classifier, which makes it hard to tell whether the gains come from the new topology or from that particular pairing. We propose an affinity-guided rewiring method that estimates the graph and the node representation together. It alternates, in the spirit of expectation maximisation, between training a lightweight graph neural network on the current graph and re-weighting candidate edges under a modularity objective with a pseudo-label homophily term. Candidate edges come from a compact pool scored by a contrastively learned node similarity and a neighbourhood-distribution affinity. The method returns two classifier-independent outputs: a rewired graph and a node embedding learned on it. Across six heterophilic benchmarks and five downstream classifiers, it improves accuracy over the original graph with normalised features in 23 of 30 classifier-dataset combinations, with a mean gain of 5.8 points, and reduces the accuracy spread between classifiers about fourfold. A controlled ablation shows that the two outputs are each useful and play complementary roles: the embedding contributes most of the accuracy gain, while the rewired graph makes different classifiers agree. A fully unsupervised variant, which uses no labels during rewiring, retains most of the improvement. The rewired graphs are also more homophilic and improve label propagation and community detection.

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/2609.32613 — 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 2026-10-07T22:14:27.727Z 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).