AI RESEARCH
Graphlets as Building Blocks for Structural Vocabulary in Knowledge Graph Foundation Models
arXiv CS.LG
•
ArXi:2605.06154v1 Announce Type: cross Foundation models excel at language, where sentences become tokens, and vision, where images become pixels, because both reduce to discrete symbols on a shared, fixed grid. Knowledge Graphs (KGs) share the discreteness, but not the geometry. Their entities and relations are discrete symbols, yet their arrangement is relational and lacks a common, fixed grid. They form irregular, non-Euclidean topologies whose local neighborhoods differ from graph to graph.