The paper introduces TOFU, a token-based foundation model for multi‑modal knowledge graph reasoning (MMKGR). TOFU converts structural, visual, and textual data into modality‑specific tokens and uses a hierarchical fusion architecture with mixture‑of‑message mechanisms to learn transferable features. Experiments on 17 MMKGs demonstrate that TOFU outperforms existing KGFM and MMKGR baselines, especially on unseen knowledge graphs.
arXiv:2607. 28980v1 Announce Type: new Abstract: Graph Foundation Models (GFMs) have recently emerged as a promising paradigm for enabling knowledge transfer across diverse domains.
arXiv:2608. 05833v1 Announce Type: new Abstract: Knowledge graph completion (KGC) aims to infer missing entities or relations from incomplete graph structures, and has evolved into multimodal knowledge graph completion (MMKGC), where entities are associated with multiple modalities such as text and images.
arXiv:2608. 08567v1 Announce Type: new Abstract: A central obstacle in building graph foundation models is the input heterogeneity in terms of feature space dimensionality, semantics, and structure.
arXiv:2605.14907v2 Announce Type: replace Abstract: Knowledge graph (KG) foundation models aim to generalize to graphs with unseen entities and relations by learning transferable relational structure...
arXiv:2507. 20804v3 Announce Type: replace Abstract: Large Language Models (LLMs) suffer from hallucinations due to their static parametric knowledge.
arXiv:2510. 09711v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and generalization capabilities beyond traditional embedding-based approaches.
KGFR introduces a Knowledge Graph Foundation Retriever that collaborates with large language models to enhance knowledge‑intensive question answering. By encoding relations with LLM‑generated descriptions and initializing entities from question roles, KGFR enables zero‑shot generalization to unseen knowledge graphs. Its Asymmetric Progressive Propagation technique efficiently handles large graphs, while a controllable reasoning loop allows the LLM to request candidate answers, supporting facts, and reasoning paths.
arXiv:2506. 22036v2 Announce Type: replace Abstract: With the increasing multimodal knowledge privatization requirements, multimodal knowledge graphs in different institutes are usually decentralized, lacking of effective collaboration system with both stronger reasoning ability and transmission safety guarantees.
arXiv:2607. 26023v1 Announce Type: new Abstract: Graph foundation models (GFMs) have emerged as a promising paradigm for transferring knowledge across graph domains and tasks.
arXiv:2606. 32016v1 Announce Type: new Abstract: Multimodal graph foundation models aim to learn reusable knowledge from graphs enriched with text, images, attributes, and relational topology, thereby supporting diverse graph-centric and modality-centric tasks.
The paper introduces a new entity alignment foundation model that overcomes the limitations of existing models by addressing the "reasoning horizon gap". It employs a parallel encoding strategy that uses seed entity pairs as local anchors to guide message passing, thereby shortening inference paths and improving alignment across sparse, heterogeneous knowledge graphs. The model also incorporates a merged relation graph and a learnable interaction module, and experimental results demonstrate its strong generalizability to unseen knowledge graphs.
The paper introduces the Structure-Internalized Rule Language Model (SIRLM) to improve Knowledge Graph Reasoning (KGR) by addressing the mismatch between KG structural context and Large Language Model (LLM) parametric knowledge. SIRLM centers on a Structure-Internalized Rule Generator (SIRG) that uses in-context learning, a structural relation memory, a KG tokenizer, and a neuro-symbolic reasoner to generate structural rules and provide faithful rule-execution feedback. Experiments on 36 datasets against 17 state‑of‑the‑art KGR methods show that SIRLM achieves significant performance gains.