Hyper-KGGen: A Skill-Driven Knowledge Extractor for High-Quality Knowledge Hypergraph Generation

• URL: http://arxiv.org/abs/2602.19543v1
• Date: Mon, 23 Feb 2026 06:32:00 GMT
• Title: Hyper-KGGen: A Skill-Driven Knowledge Extractor for High-Quality Knowledge Hypergraph Generation
• Authors: Rizhuo Huang, Yifan Feng, Rundong Xue, Shihui Ying, Jun-Hai Yong, Chuan Shi, Shaoyi Du, Yue Gao,
• Abstract summary: Hyper-KGGen is a skill-driven framework that reformulates extraction as a skill-evolving process.<n>It incorporates an textitadaptive skill acquisition module that actively distills domain expertise into a Global Skill Library.<n>We present textbfHyperDocRED, a rigorously annotated benchmark for document-level knowledge hypergraph extraction.
• Score: 63.4604143884703
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge hypergraphs surpass traditional binary knowledge graphs by encapsulating complex $n$-ary atomic facts, providing a more comprehensive paradigm for semantic representation. However, constructing high-quality hypergraphs remains challenging due to the \textit{scenario gap}: generic extractors struggle to generalize across diverse domains with specific jargon, while existing methods often fail to balance structural skeletons with fine-grained details. To bridge this gap, we propose \textbf{Hyper-KGGen}, a skill-driven framework that reformulates extraction as a dynamic skill-evolving process. First, Hyper-KGGen employs a \textit{coarse-to-fine} mechanism to systematically decompose documents, ensuring full-dimensional coverage from binary links to complex hyperedges. Crucially, it incorporates an \textit{adaptive skill acquisition} module that actively distills domain expertise into a Global Skill Library. This is achieved via a stability-based feedback loop, where extraction stability serves as a relative reward signal to induce high-quality skills from unstable traces and missed predictions. Additionally, we present \textbf{HyperDocRED}, a rigorously annotated benchmark for document-level knowledge hypergraph extraction. Experiments demonstrate that Hyper-KGGen significantly outperforms strong baselines, validating that evolved skills provide substantially richer guidance than static few-shot examples in multi-scenario settings.

Related papers

• Cross-Granularity Hypergraph Retrieval-Augmented Generation for Multi-hop Question Answering [49.43814054718318]
  Multi-hop question answering (MHQA) requires integrating knowledge scattered across multiple passages to derive the correct answer.<n>Traditional retrieval-augmented generation (RAG) methods primarily focus on coarse-grained textual semantic similarity.<n>We propose a novel RAG approach called HGRAG for MHQA that achieves cross-granularity integration of structural and semantic information via hypergraphs.
  arXiv  Detail & Related papers  (2025-08-15T06:36:13Z)
• Implicit Hypergraph Neural Networks: A Stable Framework for Higher-Order Relational Learning with Provable Guarantees [8.5183483099116]
  We introduce Implicit Hypergraph Neural Networks (IHGNN), which computes representations as the solution to a nonlinear fixed-point equation.<n>IHGNN consistently outperforms strong traditional graph/hypergraph neural network baselines in both accuracy and robustness.
  arXiv  Detail & Related papers  (2025-08-13T02:06:29Z)
• Lower Ricci Curvature for Hypergraphs [3.9965784551765697]
  We introduce hypergraph lower curvature (HLRC), a novel curvature metric defined in closed form that achieves a principled balance between interpretability and efficiency.<n>HLRC consistently reveals meaningful higher-order organization, distinguishing intra-community hyperedges, uncovering latent semantic labels, tracking temporal dynamics, and supporting robust clustering of hypergraphs based on global structure.
  arXiv  Detail & Related papers  (2025-06-04T13:32:09Z)
• TrustRAG: An Information Assistant with Retrieval Augmented Generation [73.84864898280719]
  TrustRAG is a novel framework that enhances acRAG from three perspectives: indexing, retrieval, and generation.<n>We open-source the TrustRAG framework and provide a demonstration studio designed for excerpt-based question answering tasks.
  arXiv  Detail & Related papers  (2025-02-19T13:45:27Z)
• HyperQuery: Beyond Binary Link Prediction [0.7100520098029438]
  We introduce a novel feature extraction technique using node level clustering and show how integrating data from node-level labels can improve system performance.<n>Our self-supervised approach achieves significant improvement over state of the art baselines on several hyperedge prediction and knowledge hypergraph completion benchmarks.
  arXiv  Detail & Related papers  (2025-01-13T22:46:24Z)
• HYGENE: A Diffusion-based Hypergraph Generation Method [6.997955138726617]
  We introduce a diffusion-based Hypergraph Generation (HYGENE) method that addresses challenges through a progressive local expansion approach.<n>Experiments demonstrated the effectiveness of HYGENE, proving its ability to closely mimic a variety of properties in hypergraphs.
  arXiv  Detail & Related papers  (2024-08-29T11:45:01Z)
• HyperBERT: Mixing Hypergraph-Aware Layers with Language Models for Node Classification on Text-Attributed Hypergraphs [16.07396492960869]
  We propose a new architecture, HyperBERT, which simultaneously models hypergraph relational structure and text-attributed hypergraphs. Results show that HyperBERT achieves a new state-of-the-art on five challenging text-attributed hypergraph node classification benchmarks.
  arXiv  Detail & Related papers  (2024-02-11T21:16:26Z)
• Hypergraph Transformer for Semi-Supervised Classification [50.92027313775934]
  We propose a novel hypergraph learning framework, HyperGraph Transformer (HyperGT) HyperGT uses a Transformer-based neural network architecture to effectively consider global correlations among all nodes and hyperedges. It achieves comprehensive hypergraph representation learning by effectively incorporating global interactions while preserving local connectivity patterns.
  arXiv  Detail & Related papers  (2023-12-18T17:50:52Z)
• Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative [126.0985540285981]
  We apply the contrastive learning approach from images/graphs (we refer to it as HyperGCL) to improve generalizability of hypergraph neural networks. We fabricate two schemes to augment hyperedges with higher-order relations encoded, and adopt three augmentation strategies from graph-structured data. We propose a hypergraph generative model to generate augmented views, and then an end-to-end differentiable pipeline to jointly learn hypergraph augmentations and model parameters.
  arXiv  Detail & Related papers  (2022-10-07T20:12:20Z)
• Hypergraph Convolutional Networks via Equivalency between Hypergraphs and Undirected Graphs [59.71134113268709]
  We present General Hypergraph Spectral Convolution(GHSC), a general learning framework that can handle EDVW and EIVW hypergraphs. In this paper, we show that the proposed framework can achieve state-of-the-art performance. Experiments from various domains including social network analysis, visual objective classification, protein learning demonstrate that the proposed framework can achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-03-31T10:46:47Z)

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.