paper-with-me

Papers

HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature

2026-03-24 · Devvrat Joshi, Islem Rekik arxiv

Automated knowledge graph (KG) construction is essential for navigating the rapidly expanding body of scientific literature. However, existing approaches struggle to recognize long multi-word entities, often fail to generalize across domains, and typically overlook the hierarchical nature of scientific knowledge. While general-purpose large language models (LLMs) offer adaptability, they are computationally expensive and yield inconsistent accuracy on specialized tasks. As a result, current KGs are shallow and inconsistent, limiting their utility for exploration and synthesis. We propose a two-stage framework for scalable, zero-shot scientific KG construction. The first stage, Z-NERD, introduces (i) Orthogonal Semantic Decomposition (OSD), which promotes domain-agnostic entity recognition by isolating semantic "turns" in text, and (ii) a Multi-Scale TCQK attention mechanism that captures coherent multi-word entities through n-gram-aware attention heads. The second stage, HGNet, performs relation extraction with hierarchy-aware message passing, explicitly modeling parent, child, and peer relations. To enforce global consistency, we introduce two complementary objectives: a Differentiable Hierarchy Loss to discourage cycles and shortcut edges, and a Continuum Abstraction Field (CAF) Loss that embeds abstraction levels along a learnable axis in Euclidean space. This is the first approach to formalize hierarchical abstraction as a continuous property within standard Euclidean embeddings, offering a simpler alternative to hyperbolic methods. We release SPHERE (https://github.com/basiralab/SPHERE), a multi-domain benchmark for hierarchical relation extraction. Our framework establishes a new state of the art on SciERC, SciER, and SPHERE, improving NER by 8.08% and RE by 5.99% on out-of-distribution tests. In zero-shot settings, gains reach 10.76% for NER and 26.2% for RE.

📄 PDF Abstract BibTeX arXiv:2603.23136

Code (0)

등록된 구현이 없습니다.

Tasks

Relation ExtractionGraph Generation

Similar Papers 제목 키워드 기반

STAHGNet: Modeling Hybrid-grained Heterogenous Dependency Efficiently for Traffic Prediction

2024-12-23 · Jiyao Wang, Zehua Peng, Yijia Zhang, Dengbo He 외

Traffic flow prediction plays a critical role in the intelligent transportation system, and it is also a challenging task because of the underlying complex Spatio-temporal patterns and heterogeneities evolving across tim…

Feature EngineeringGraph AttentionTraffic Prediction

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs

2024-12-30 · Yuanchang Zhou, Siyu Hu, Chen Wang, Lin-Wang Wang 외

Graph neural network universal interatomic potentials (GNN-UIPs) have demonstrated remarkable generalization and transfer capabilities in material discovery and property prediction. These models can accelerate molecular …

GPUGraph Neural NetworkProperty Prediction

Predicting Brain Multigraph Population From a Single Graph Template for Boosting One-Shot Classification

2022-09-13 · Furkan Pala, Islem Rekik

A central challenge in training one-shot learning models is the limited representativeness of the available shots of the data space. Particularly in the field of network neuroscience where the brain is represented as a g…

Data AugmentationGraph Neural NetworkOne-Shot Learning

PHGNet: Prototype-Guided Hypergraph Construction for Heterogeneous Spatiotemporal Forecasting

2026-05-25 · Ruiwen Gu, Yahao Liu, Zhenyu Liu, Qitai Tan 외 arxiv

As a core task in intelligent transportation systems, traffic forecasting plays a critical role in urban traffic management. Accurate traffic forecasting relies on modeling complex spatiotemporal dependencies, which is i…

Hierarchical Knowledge Graph Construction from Images for Scalable E-Commerce

2024-10-28 · Zhantao Yang, Han Zhang, Fangyi Chen, Anudeepsekhar Bolimera 외

Knowledge Graph (KG) is playing an increasingly important role in various AI systems. For e-commerce, an efficient and low-cost automated knowledge graph construction method is the foundation of enabling various successf…

Benchmarkinggraph constructionKnowledge GraphsLanguage Modeling+2