HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Relation ExtractionGraph GenerationSimilar Papers 제목 키워드 기반
STAHGNet: Modeling Hybrid-grained Heterogenous Dependency Efficiently for Traffic Prediction
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 PredictionFastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs
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 PredictionPredicting Brain Multigraph Population From a Single Graph Template for Boosting One-Shot Classification
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 LearningPHGNet: Prototype-Guided Hypergraph Construction for Heterogeneous Spatiotemporal Forecasting
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
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