Every Little Helps: Building Knowledge Graph Foundation Model with Fine-grained Transferable Multi-modal Tokens

TL;DR

This paper introduces TOFU, a token-based foundation model for multi-modal knowledge graph reasoning that effectively generalizes across different datasets by leveraging fine-grained, modality-specific tokens and hierarchical fusion.

Contribution

It proposes a novel token-based architecture that discretizes multi-modal information and employs hierarchical fusion, enabling strong cross-knowledge graph transfer and generalization.

Findings

Outperforms existing models on 17 MMKGs

Demonstrates strong generalization to unseen MMKGs

Effective across transductive, inductive, and fully-inductive settings

Abstract

Multi-modal knowledge graph reasoning (MMKGR) aims to predict the missing links by exploiting both graph structure information and multi-modal entity contents. Most existing works are designed for a transductive setting, which learns dataset-specific embeddings and struggles to generalize to new KGs. Recent knowledge graph foundation models (KGFMs) improve cross-KG transfer, but they mainly exploit structural patterns and ignore rich multi-modal signals. We address these gaps by proposing a token-based foundation model (TOFU) for MMKGR, which exhibits strong generalization across different MMKGs. TOFU discretizes structural, visual, and textual information into modality-specific tokens. TOFU then employs a hierarchical fusion architecture with mixture-of-message mechanisms, aiming to process these tokens and obtain transferable features for MMKGR. Experimental results on 17 transductive, inductive, and fully-inductive MMKGs show that TOFU consistently outperforms strong KGFM and MMKGR baselines, delivering strong performance on unseen MMKGs.