Beyond Completion: A Foundation Model for General Knowledge Graph Reasoning

• URL: http://arxiv.org/abs/2505.21926v1
• Date: Wed, 28 May 2025 03:21:28 GMT
• Title: Beyond Completion: A Foundation Model for General Knowledge Graph Reasoning
• Authors: Yin Hua, Zhiqiang Liu, Mingyang Chen, Zheng Fang, Chi Man Wong, Lingxiao Li, Chi Man Vong, Huajun Chen, Wen Zhang,
• Abstract summary: MERRY is a foundation model for general knowledge graph reasoning.<n>We propose a Conditional Message Passing (CMP) encoding architecture to bridge the gap between textual and structural modalities.<n> Comprehensive evaluations on 28 datasets demonstrate that MERRY outperforms existing baselines in most scenarios.
• Score: 42.93788746991493
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In natural language processing (NLP) and computer vision (CV), the successful application of foundation models across diverse tasks has demonstrated their remarkable potential. However, despite the rich structural and textual information embedded in knowledge graphs (KGs), existing research of foundation model for KG has primarily focused on their structural aspects, with most efforts restricted to in-KG tasks (e.g., knowledge graph completion, KGC). This limitation has hindered progress in addressing more challenging out-of-KG tasks. In this paper, we introduce MERRY, a foundation model for general knowledge graph reasoning, and investigate its performance across two task categories: in-KG reasoning tasks (e.g., KGC) and out-of-KG tasks (e.g., KG question answering, KGQA). We not only utilize the structural information, but also the textual information in KGs. Specifically, we propose a multi-perspective Conditional Message Passing (CMP) encoding architecture to bridge the gap between textual and structural modalities, enabling their seamless integration. Additionally, we introduce a dynamic residual fusion module to selectively retain relevant textual information and a flexible edge scoring mechanism to adapt to diverse downstream tasks. Comprehensive evaluations on 28 datasets demonstrate that MERRY outperforms existing baselines in most scenarios, showcasing strong reasoning capabilities within KGs and excellent generalization to out-of-KG tasks such as KGQA.

Related papers

• Grounding LLM Reasoning with Knowledge Graphs [4.279373869671241]
  We propose integrating reasoning strategies with Knowledge Graphs to anchor every step or "thought" of the reasoning chains in KG data.<n>We evaluate both agentic and automated search methods across several reasoning strategies, including Chain-of-Thought (CoT), Tree-of-Thought (ToT), and Graph-of-Thought (GoT)<n>Our experiments demonstrate that this approach consistently outperforms baseline models.
  arXiv  Detail & Related papers  (2025-02-18T19:20:46Z)
• GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion [52.026016846945424]
  We propose a new method called GLTW, which encodes the structural information of KGs and merges it with Large Language Models.<n>Specifically, we introduce an improved Graph Transformer (iGT) that effectively encodes subgraphs with both local and global structural information.<n>Also, we develop a subgraph-based multi-classification training objective, using all entities within KG as classification objects, to boost learning efficiency.
  arXiv  Detail & Related papers  (2025-02-17T06:02:59Z)
• KG-TRICK: Unifying Textual and Relational Information Completion of Knowledge for Multilingual Knowledge Graphs [17.447946165398932]
  We introduce KG-TRICK, a novel sequence-to-sequence framework that unifies the tasks of textual and relational information completion for multilingual knowledge graphs.<n> KG-TRICK demonstrates that: i) it is possible to unify the tasks of KGC and KGE into a single framework, and ii) combining textual information from multiple languages is beneficial to improve the completeness of a KG.<n>As part of our contributions, we also introduce WikiKGE10++, the largest manually-curated benchmark for textual information completion of KGs.
  arXiv  Detail & Related papers  (2025-01-07T06:21:40Z)
• Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains [66.55612528039894]
  Knowledge Graphs (KGs) can serve as reliable knowledge sources for question answering (QA) We present DoG (Decoding on Graphs), a novel framework that facilitates a deep synergy between LLMs and KGs. Experiments across various KGQA tasks with different background KGs demonstrate that DoG achieves superior and robust performance.
  arXiv  Detail & Related papers  (2024-10-24T04:01:40Z)
• A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning [17.676185326247946]
  We propose a prompt-based KG foundation model via in-context learning, namely KG-ICL, to achieve a universal reasoning ability. To encode prompt graphs with the generalization ability to unseen entities and relations in queries, we first propose a unified tokenizer. Then, we propose two message passing neural networks to perform prompt encoding and KG reasoning, respectively.
  arXiv  Detail & Related papers  (2024-10-16T06:47:18Z)
• Context Graph [8.02985792541121]
  We present a context graph reasoning textbfCGR$3$ paradigm that leverages large language models (LLMs) to retrieve candidate entities and related contexts. Our experimental results demonstrate that CGR$3$ significantly improves performance on KG completion (KGC) and KG question answering (KGQA) tasks.
  arXiv  Detail & Related papers  (2024-06-17T02:59:19Z)
• Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering [87.67177556994525]
  We propose a training-free method called Generate-on-Graph (GoG) to generate new factual triples while exploring Knowledge Graphs (KGs) GoG performs reasoning through a Thinking-Searching-Generating framework, which treats LLM as both Agent and KG in IKGQA.
  arXiv  Detail & Related papers  (2024-04-23T04:47:22Z)
• Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey [61.8716670402084]
  This survey focuses on KG-aware research in two principal aspects: KG-driven Multi-Modal (KG4MM) learning, and Multi-Modal Knowledge Graph (MM4KG) Our review includes two primary task categories: KG-aware multi-modal learning tasks, and intrinsic MMKG tasks. For most of these tasks, we provide definitions, evaluation benchmarks, and additionally outline essential insights for conducting relevant research.
  arXiv  Detail & Related papers  (2024-02-08T04:04:36Z)
• KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Models [18.20425100517317]
  We propose KG-GPT, a framework leveraging large language models for tasks employing knowledge graphs. KG-GPT comprises three steps: Sentence, Graph Retrieval, and Inference, each aimed at partitioning sentences, retrieving relevant graph components, and deriving logical conclusions. We evaluate KG-GPT using KG-based fact verification and KGQA benchmarks, with the model showing competitive and robust performance, even outperforming several fully-supervised models.
  arXiv  Detail & Related papers  (2023-10-17T12:51:35Z)
• Reasoning over Multi-view Knowledge Graphs [59.99051368907095]
  ROMA is a novel framework for answering logical queries over multi-view KGs. It scales up to KGs of large sizes (e.g., millions of facts) and fine-granular views. It generalizes to query structures and KG views that are unobserved during training.
  arXiv  Detail & Related papers  (2022-09-27T21:32:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.