Graphlets as Building Blocks for Structural Vocabulary in Knowledge Graph Foundation Models

2026-05-07

AI Summary

Existing knowledge graphs lack a unified structured vocabulary, which limits the transferability of foundation models across unseen graphs. This work proposes graphlets as universal structural tokens and introduces, for the first time, a systematic framework of model-agnostic structural vocabularies based on closed and open 2- and 3-paths as well as star-shaped graphlets. By leveraging pattern matching to uncover local topological invariances among relations, the approach enables zero-shot inductive and transductive link prediction. Evaluated across 51 cross-domain knowledge graphs, the method significantly outperforms current knowledge graph foundation models, demonstrating the effectiveness of graphlet-based vocabularies in enhancing cross-graph generalization.

Abstract

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 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. Knowledge Graphs (KGs) share the discreteness, but not the geometry. They form irregular, non-Euclidean topologies whose local neighborhoods differ from graph to graph. Therefore, Knowledge Graph Foundation Models (KGFMs) rely on identifying structural invariances to produce transferable representations. Without a universal token set, KGFMs are limited in their ability to transfer representations across unseen KGs. We close this gap by treating graphlets, small connected graphs, as structural tokens that recur in heterogeneous KGs. In this paper, We introduce a model-agnostic framework based on a vocabulary of graphlets that mines a KG between relations via pattern matching. In particular, we considered closed and open 2- and 3-path, and star graphlets, to obtain robust invariances. The framework is evaluated on 51 KGs from a wide range of domains, for zero-shot inductive and transductive link prediction. Experiments show that adding simple graphlets to the vocabulary yields models that outperform prior KGFMs.

Problem

• Knowledge Graph Foundation Models
• structural invariances
• graphlets
• representation transfer
• non-Euclidean topology

Innovation

• graphlets
• knowledge graph foundation models
• structural vocabulary
• zero-shot link prediction
• model-agnostic framework