ACL Findings2024
Enhancing Hyperbolic Knowledge Graph Embeddings via Lorentz Transformations
Xiran Fan, Minghua Xu, Huiyuan Chen, Yuzhong Chen, Mahashweta Das, Hao Yang
Abstract
Knowledge Graph Embedding (KGE) is a powerful technique for predicting missing links in Knowledge Graphs (KGs) by learning the entities and relations. Hyperbolic space has emerged as a promising embedding space for KGs due to its ability to represent hierarchical data. Nevertheless, most existing hyperbolic KGE methods rely on tangent approximation and are not fully hyperbolic, resulting in distortions and inaccuracies. To overcome this limitation, we propose LorentzKG, a fully hyperbolic KGE method that represents entities as points in the Lorentz model and represents relations as the intrinsic transformation-the Lorentz transformations between entities. We demonstrate that the Lorentz transformation, which can be decomposed into Lorentz rotation/reflection and Lorentz boost, captures various types of relations including hierarchical structures. Experimental results show that our LorentzKG achieves state-of-the-art performance 1 .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
5 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- NumCoKE: Ordinal-Aware Numerical Reasoning over Knowledge Graphs with Mixture-of-Experts and Contrastive Learning cites Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones
- NumCoKE: Ordinal-Aware Numerical Reasoning over Knowledge Graphs with Mixture-of-Experts and Contrastive Learning cites Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction
- A Mixed-Curvature based Pre-training Paradigm for Multi-Task Vehicle Routing Solver cites Mixed-Curvature Multi-Relational Graph Neural Network for Knowledge Graph Completion
- Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones cites Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction
- FlorE: Integrating Full Lorentz Group and Directional Offsets for Effective Knowledge Graph Embedding cites Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction
- FlorE: Integrating Full Lorentz Group and Directional Offsets for Effective Knowledge Graph Embedding cites CoDEx: A Comprehensive Knowledge Graph Completion Benchmark
- Mixed-Curvature Multi-Relational Graph Neural Network for Knowledge Graph Completion cites Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction
Cited by top-tier papers5
- Intrinsic Lorentz Neural NetworkXianglong Shi, Ziheng Chen, Yunhan Jiang, Nicu SebeICLR 2026 · 3 citations
- HyperKGR: Knowledge Graph Reasoning in Hyperbolic Space with Graph Neural Network Encoding Symbolic PathLihui LiuEMNLP 2025 · 2 citations
- NumCoKE: Ordinal-Aware Numerical Reasoning over Knowledge Graphs with Mixture-of-Experts and Contrastive LearningMing Yin, Zongsheng Cao, Qiqing Xia, Chenyang Tu et al.AAAI 2026 · 1 citation
- A Mixed-Curvature based Pre-training Paradigm for Multi-Task Vehicle Routing SolverSuyu Liu, Zhiguang Cao, Shanshan Feng, Yew-Soon OngICML 2025
- FlorE: Integrating Full Lorentz Group and Directional Offsets for Effective Knowledge Graph EmbeddingZehua Duo, Jiang Li, Xiangdong Su, Guanglai GaoAAAI 2026
Builds on13
- Learning Hierarchy-Aware Knowledge Graph Embeddings for Link PredictionZhanqiu Zhang, Jianyu Cai, Yongdong Zhang, Jie WangAAAI 2020 · 481 citations
- LLM Maybe LongLM: SelfExtend LLM Context Window Without TuningHongye Jin, Xiaotian Han, Jingfeng Yang, Zhimeng Jiang et al.ICML 2024 · 167 citations
- Mixed-Curvature Multi-Relational Graph Neural Network for Knowledge Graph CompletionShen Wang, Xiaokai Wei, Cícero Nogueira dos Santos, Zhiguo Wang et al.WWW 2021 · 122 citations
- CoDEx: A Comprehensive Knowledge Graph Completion BenchmarkTara Safavi, Danai KoutraEMNLP 2020 · 97 citations
- Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic ConesYushi Bai, Zhitao Ying, Hongyu Ren, Jure LeskovecNeurIPS 2021 · 84 citations
Related papers
- Hyperbolic Hierarchy-Aware Knowledge Graph Embedding for Link PredictionZhe Pan, Peng WangEMNLP Findings 2021 · 30 citations
- Low-Dimensional Hyperbolic Knowledge Graph EmbeddingsInes Chami, Adva Wolf, Da-Cheng Juan, Frederic Sala et al.ACL 2020 · 48 citations
- Geometry Interaction Knowledge Graph EmbeddingsZongsheng Cao, Qianqian Xu, Zhiyong Yang, Xiaochun Cao et al.AAAI 2022 · 81 citations
- Complex Hyperbolic Knowledge Graph Embeddings with Fast Fourier TransformHuiru Xiao, Xin Liu, Yangqiu Song, Ginny Y. Wong et al.EMNLP 2022 · 9 citations
- Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph EmbeddingsKai Wang, Yu Liu, Dan Lin, Michael ShengEMNLP Findings 2021 · 16 citations
