Graphlets as Building Blocks for Structural Vocabulary in Graph Foundation Models

Kossi Amouzouvi, Robert Wardenga, Jens Lehmann, Sahar Vahdati

Keywords: Knowledge Graph, Graph Foundation Model, Knowledge Graph Representation Learning, Graphlets

TL;DR: This paper investigates Graphlets as structural vocabulary to improve transferability and performance of Knowledge Graph Foundation Models.

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, Graph Foundation Models (GFMs) rely on identifying structural invariances to produce transferable representations. Without a universal token set, GFMs 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 GFMs.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 11511