SOURCE-LINKED INTELLIGENCE

Reification as a Transferable Vocabulary: Zero-Shot Link Prediction with Vanilla GNNs

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

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, GraphSAG

Read original source ↗ Open in workspace

recordType

paper

region

Global