Half a Link can Be Enough to Predict a Whole Link: Understanding Generalization in Knowledge Graph Foundation Models

2026-06-16

AI Summary

The zero-shot generalization mechanism of knowledge graph foundation models on unseen graphs remains poorly understood, particularly under scenarios with partially observed relations (semi-links), where performance is often unstable. This work introduces four fine-grained generalization settings based on the visibility of head-relation or relation-tail semi-links, establishes a diagnostic evaluation protocol, and systematically assesses state-of-the-art models using a hierarchical zero-shot link prediction strategy. Experimental results reveal that current advanced models heavily rely on observed semi-links for inference and suffer significant performance degradation when confronted with entirely unseen semi-links. These findings underscore the critical role of semi-link visibility in zero-shot generalization and provide clear guidance for future model design.

Abstract

Knowledge graph (KG) foundation models (KGFMs) are zero-shot generalizers: trained once, they can predict links on unseen graphs without retraining. However, understanding when and how they can robustly generalize across KGs is still an open question. In this paper, we shed some light on their generalization mechanisms highlighting how their performance on unseen KGs is not uniform when it comes to partially seen links, which we call half-links. In fact, we show that to predict a test triple $(h,r,t)$ it might suffice in practice to have observed the half-link $(h,r)$ or $(r,t)$ in the inference graph. This yields a taxonomy of four scenarios when combinations of these half-links are observed or not. In a rigorous stratified analysis over these scenarios, we reveal that SoTA KGFMs use seen half links for predictions, while unseen half-links pose different challenges. As such, our finer-grained taxonomy can be a diagnostic protocol for robust KGFM generalization and highlights where novel KGFMs can improve.

Problem

• knowledge graph foundation models
• zero-shot generalization
• link prediction
• half-links
• out-of-distribution generalization

Innovation

• knowledge graph foundation models
• zero-shot generalization
• half-link
• link prediction
• out-of-distribution generalization