Metraipolis › archive › dc_504cd1c8343b
Reification as a Transferable Vocabulary: Zero-Shot Link Prediction with Vanilla GNNs — arXiv:2609.11347
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11347
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T05:27:02.105Z
- SHA-256 of the archived text
d5990fff15116ce45a47c25f18c45662303454ed7b4be024aba089e2f8e050bb- Stable URL of this page
https://metraipolis.com/documento/dc_504cd1c8343b
How to cite
Reification as a Transferable Vocabulary: Zero-Shot Link Prediction with Vanilla GNNs — arXiv:2609.11347 — arXiv (en), https://arxiv.org/abs/2609.11347 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_504cd1c8343b (Metraipolis archive dc_504cd1c8343b, sha256 d5990fff15116ce45a47c25f18c45662303454ed7b4be024aba089e2f8e050bb)
BibTeX
@misc{dc504cd1c8343b,
title = {Reification as a Transferable Vocabulary: Zero-Shot Link Prediction with Vanilla GNNs — arXiv:2609.11347},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11347},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_504cd1c8343b; sha256 d5990fff15116ce45a47c25f18c45662303454ed7b4be024aba089e2f8e050bb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11347. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Knowledge graph foundation models such as ULTRA achieve zero-shot link prediction on unseen graphs through dedicated architectures that hard-code a transfer mechanism. In this work we move that mechanism out of the architecture and into the representation, by \emph{reifying} the input graph: every fact becomes a node, connected to its subject, object, and relation type through a fixed vocabulary of six meta-relations, with relation types as anonymous shared nodes rather than model parameters. On this representation, five textbook GNNs (GAT, GINE with sum and with mean+max aggregation, GraphSAGE, R-GCN), each trained on a single knowledge graph of 4,245 triples for 30 minutes on one NVIDIA A100, transfer zero-shot to 40 inductive link-prediction benchmarks. The best of them, an off-the-shelf GAT, matches ULTRA, a dedicated foundation model pretrained on three graphs, across ULTRA's own evaluation suite. The same fixed vocabulary extends to relational databases, a row becoming an entity and a foreign-key column a relation type; a preliminary probe on two unseen databases, with no cell values, schema text or in-context labels, shows a model of this family pretrained on three knowledge graphs ranking foreign-key targets far above random-initialization and degree controls. We release the code, the checkpoints, and the evaluation pipeline for all 40 benchmarks.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.11347 — 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 2026-10-16T05:17:52.154Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).