Metraipolis › archive › dc_bc42ea05389c

The Universal Classifier for Graph Learning — arXiv:2609.36302

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36302
License (as archived)
CC0-1.0
Archived
2026-10-07T17:28:58.906Z
SHA-256 of the archived text
226d8444d3916a3fd6f698fd05e914326c11b31d1a1af15329150314e7aead96
Stable URL of this page
https://metraipolis.com/documento/dc_bc42ea05389c

How to cite

The Universal Classifier for Graph Learning — arXiv:2609.36302 — arXiv (en), https://arxiv.org/abs/2609.36302 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc42ea05389c (Metraipolis archive dc_bc42ea05389c, sha256 226d8444d3916a3fd6f698fd05e914326c11b31d1a1af15329150314e7aead96)
BibTeX
@misc{dcbc42ea05389c,
  title = {The Universal Classifier for Graph Learning — arXiv:2609.36302},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36302},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc42ea05389c; sha256 226d8444d3916a3fd6f698fd05e914326c11b31d1a1af15329150314e7aead96},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36302. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While foundation models have revolutionized natural language processing and computer vision by leveraging universal vocabularies, Graph Machine Learning (GML) remains fractured due to the absence of a unified feature and structural representation across diverse domains. Existing works claiming to be Graph Foundation Models (GFMs) are typically restricted to node-level predictions or require fixed feature dimensions, failing to provide a truly task-agnostic backbone for the full spectrum of graph learning applications. In this paper, we introduce the Universal Classifier (UC), which supports arbitrary feature and class cardinalities, unifying node-, edge-, and graph-level objectives under a single similarity-based classification objective. The UC reformulates all node-, edge-, and graph-level prediction tasks as maximizing similarity in the latent space: by lifting heterogeneous features and labels into 3D latent tensors, the model learns transferable features independent of specific input schemas. This architecture allows a single pre-trained model to generalize to node classification, node regression, and link prediction across unseen graphs with varying feature semantics. Experiments show strong zero-shot transfer performance across node-, link-, and graph-level tasks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.36302 — 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 2026-10-07T16:59:48.151Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).