SEMMA: A Semantic Aware Knowledge Graph Foundation Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Arun, Arvindh, Kumar, Sumit, Nayyeri, Mojtaba, Xiong, Bo, Kumaraguru, Ponnurangam, Vergari, Antonio, Staab, Steffen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915501990477824
author Arun, Arvindh
Kumar, Sumit
Nayyeri, Mojtaba
Xiong, Bo
Kumaraguru, Ponnurangam
Vergari, Antonio
Staab, Steffen
author_facet Arun, Arvindh
Kumar, Sumit
Nayyeri, Mojtaba
Xiong, Bo
Kumaraguru, Ponnurangam
Vergari, Antonio
Staab, Steffen
contents Knowledge Graph Foundation Models (KGFMs) have shown promise in enabling zero-shot reasoning over unseen graphs by learning transferable patterns. However, most existing KGFMs rely solely on graph structure, overlooking the rich semantic signals encoded in textual attributes. We introduce SEMMA, a dual-module KGFM that systematically integrates transferable textual semantics alongside structure. SEMMA leverages Large Language Models (LLMs) to enrich relation identifiers, generating semantic embeddings that subsequently form a textual relation graph, which is fused with the structural component. Across 54 diverse KGs, SEMMA outperforms purely structural baselines like ULTRA in fully inductive link prediction. Crucially, we show that in more challenging generalization settings, where the test-time relation vocabulary is entirely unseen, structural methods collapse while SEMMA is 2x more effective. Our findings demonstrate that textual semantics are critical for generalization in settings where structure alone fails, highlighting the need for foundation models that unify structural and linguistic signals in knowledge reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20422
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SEMMA: A Semantic Aware Knowledge Graph Foundation Model
Arun, Arvindh
Kumar, Sumit
Nayyeri, Mojtaba
Xiong, Bo
Kumaraguru, Ponnurangam
Vergari, Antonio
Staab, Steffen
Computation and Language
Artificial Intelligence
Knowledge Graph Foundation Models (KGFMs) have shown promise in enabling zero-shot reasoning over unseen graphs by learning transferable patterns. However, most existing KGFMs rely solely on graph structure, overlooking the rich semantic signals encoded in textual attributes. We introduce SEMMA, a dual-module KGFM that systematically integrates transferable textual semantics alongside structure. SEMMA leverages Large Language Models (LLMs) to enrich relation identifiers, generating semantic embeddings that subsequently form a textual relation graph, which is fused with the structural component. Across 54 diverse KGs, SEMMA outperforms purely structural baselines like ULTRA in fully inductive link prediction. Crucially, we show that in more challenging generalization settings, where the test-time relation vocabulary is entirely unseen, structural methods collapse while SEMMA is 2x more effective. Our findings demonstrate that textual semantics are critical for generalization in settings where structure alone fails, highlighting the need for foundation models that unify structural and linguistic signals in knowledge reasoning.
title SEMMA: A Semantic Aware Knowledge Graph Foundation Model
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.20422