UniHR: Hierarchical Representation Learning for Unified Knowledge Graph Link Prediction

2024-11-11 · Zhiqiang Liu, Yin Hua, Mingyang Chen, Zhuo Chen, Ziqi Liu, Lei Liang, Huajun Chen, Wen Zhang

Beyond-triple fact representations including hyper-relational facts with auxiliary key-value pairs, temporal facts with additional timestamps, and nested facts implying relationships between facts, are gaining significant attention. However, constrained by complex fact representation forms, existing link prediction models for beyond-triple facts have difficulty achieving hierarchical fact modeling and generalizing the modules for one specific facts to other fact types. To overcome this limitation, we propose a Unified Hierarchical Representation learning framework (UniHR) for unified knowledge graph link prediction. It consists of a unified Hierarchical Data Representation (HiDR) module and a unified Hierarchical Structure Learning (HiSL) module as graph encoder. The HiDR module unifies hyper-relational KGs, temporal KGs, and nested factual KGs into triple-based representations. Then HiSL incorporates intra-fact and inter-fact message passing, focusing on enhancing the semantic information within individual facts and enriching the structural information between facts. Empirical results demonstrate the effectiveness of UniHR and highlight the strong potential of unified representations. Code and data are available at https://github.com/Lza12a/UniHR.

📄 PDF Abstract BibTeX arXiv:2411.07019

Code (1)

lza12a/unihr 공식 구현 pytorch

Tasks

Link Prediction Representation Learning

Hierarchical Knowledge Graphs: A Novel Information Representation for Exploratory Search Tasks

2020-05-04 · Bahareh Sarrafzadeh, Adam Roegiest, Edward Lank

In exploratory search tasks, alongside information retrieval, information representation is an important factor in sensemaking. In this paper, we explore a multi-layer extension to knowledge graphs, hierarchical knowledg…

Information Retrieval Knowledge Graphs Retrieval

Biomedical Event Extraction with Hierarchical Knowledge Graphs

2020-09-20 · Findings of the Association for Computational Linguistics 2020 · Kung-Hsiang Huang, Mu Yang, Nanyun Peng

Biomedical event extraction is critical in understanding biomolecular interactions described in scientific corpus. One of the main challenges is to identify nested structured events that are associated with non-indicativ…

Event Extraction Language Modeling Sentence

KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs

2021-09-09 · Yinquan Lu, Haonan Lu, Guirong Fu, Qun Liu

Incorporating factual knowledge into pre-trained language models (PLM) such as BERT is an emerging trend in recent NLP studies. However, most of the existing methods combine the external knowledge integration module with…

Common Sense Reasoning Language Modelling Machine Reading Comprehension Question Answering+2

A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation

2026-06-16 · Haoyang Zhong, Yifei Sun, Antong Zhang, Chunping Wang 외 arxiv

Retrieval-Augmented Generation (RAG) has emerged as a paradigm for enhancing large language models (LLMs) with external knowledge, yet existing graph-based methods face a fundamental limitation: entity-centric and chunk-…

VDGR-RAG: Vectors, Directories, Graphs, and Reflection Are All You Need for Unified Reasoning over Hierarchical Enterprise Knowledge

2026-08-08 · Wenqi Chen, Haofei Yang, Rui Yang, Fangming Li arxiv

Retrieval-Augmented Generation (RAG) is essential for enterprise knowledge question answering (QA), particularly in domains with complex product documentation like telecommunications. However, existing RAG approaches lar…

Question Answering