A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning

2024-10-16 · Yuanning Cui, Zequn Sun, Wei Hu

Extensive knowledge graphs (KGs) have been constructed to facilitate knowledge-driven tasks across various scenarios. However, existing work usually develops separate reasoning models for different KGs, lacking the ability to generalize and transfer knowledge across diverse KGs and reasoning settings. In this paper, we propose a prompt-based KG foundation model via in-context learning, namely KG-ICL, to achieve a universal reasoning ability. Specifically, we introduce a prompt graph centered with a query-related example fact as context to understand the query relation. To encode prompt graphs with the generalization ability to unseen entities and relations in queries, we first propose a unified tokenizer that maps entities and relations in prompt graphs to predefined tokens. Then, we propose two message passing neural networks to perform prompt encoding and KG reasoning, respectively. We conduct evaluation on 43 different KGs in both transductive and inductive settings. Results indicate that the proposed KG-ICL outperforms baselines on most datasets, showcasing its outstanding generalization and universal reasoning capabilities. The source code is accessible on GitHub: https://github.com/nju-websoft/KG-ICL.

📄 PDF Abstract BibTeX arXiv:2410.12288

Code (1)

nju-websoft/KG-ICL 공식 구현 pytorch

Tasks

In-Context LearningKnowledge Graphs

Learning and Editing Universal Graph Prompt Tuning via Reinforcement Learning

2025-12-09 · Jinfeng Xu, Zheyu Chen, Shuo Yang, Jinze Li 외 arxiv

Early graph prompt tuning approaches relied on task-specific designs for Graph Neural Networks (GNNs), limiting their adaptability across diverse pre-training strategies. In contrast, another promising line of research h…

Reinforcement Learning

TFMLinker: Universal Link Predictor by Graph In-Context Learning with Tabular Foundation Models

2026-02-09 · Tianyin Liao, Chunyu Hu, Yicheng Sui, Xingxuan Zhang 외 arxiv

Link prediction is a fundamental task in graph machine learning with widespread applications such as recommendation systems, drug discovery, knowledge graphs, etc. In the foundation model era, how to develop universal li…

Recommendation Systems Knowledge Graphs Link Prediction Drug Discovery

GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning

2025-11-05 · Haonan Yuan, Qingyun Sun, Junhua Shi, Xingcheng Fu 외 arxiv

Inspired by the remarkable success of foundation models in language and vision, Graph Foundation Models (GFMs) hold significant promise for broad applicability across diverse graph tasks and domains. However, existing GF…

Graph Classification Graph Similarity

KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning

2026-05-14 · Yisen Gao, Jiaxin Bai, Haoyu Huang, Zhongwei Xie 외 arxiv

Knowledge graph (KG) foundation models aim to generalize across graphs with unseen entities and relations by learning transferable relational structure. However, most existing methods primarily emphasize relation-level u…

Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation

2026-01-15 · Chongcong Jiang, Tianxingjian Ding, Chuhan Song, Jiachen Tu 외 arxiv

Promptable segmentation foundation models such as SAM3 have demonstrated strong generalization capabilities through interactive and concept-based prompting. However, their direct applicability to medical image segmentati…

Medical Image Segmentation Prompt Engineering