EMNLP Findings2021
Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings
Abstract
Recent knowledge graph embedding (KGE) models based on hyperbolic geometry have shown great potential in a low-dimensional embedding space. However, the necessity of hyperbolic space in KGE is still questionable, because the calculation based on hyperbolic geometry is much more complicated than Euclidean operations. In this paper, based on the state-of-the-art hyperbolic-based model RotH, we develop two lightweight Euclideanbased models, called RotL and Rot2L. The RotL model simplifies the hyperbolic operations while keeping the flexible normalization effect. Utilizing a novel two-layer stacked transformation and based on RotL, the Rot2L model obtains an improved representation capability, yet costs fewer parameters and calculations than RotH. The experiments on link prediction show that Rot2L achieves the stateof-the-art performance on two widely-used datasets in low-dimensional knowledge graph embeddings. Furthermore, RotL achieves similar performance as RotH but only requires half of the training time.
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.
4 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
- Ultrahyperbolic Knowledge Graph Embeddings cites Low-Dimensional Hyperbolic Knowledge Graph Embeddings
- Swift and Sure: Hardness-aware Contrastive Learning for Low-dimensional Knowledge Graph Embeddings cites Composition-based Multi-Relational Graph Convolutional Networks
- Swift and Sure: Hardness-aware Contrastive Learning for Low-dimensional Knowledge Graph Embeddings cites Low-Dimensional Hyperbolic Knowledge Graph Embeddings
- Complex Hyperbolic Knowledge Graph Embeddings with Fast Fourier Transform cites Low-Dimensional Hyperbolic Knowledge Graph Embeddings
- Knowledge Association with Hyperbolic Knowledge Graph Embeddings cites Hyperbolic Neural Networks++
- Knowledge Association with Hyperbolic Knowledge Graph Embeddings cites Composition-based Multi-Relational Graph Convolutional Networks
- TIGER: Training Inductive Graph Neural Network for Large-scale Knowledge Graph Reasoning cites Swift and Sure: Hardness-aware Contrastive Learning for Low-dimensional Knowledge Graph Embeddings
- TIGER: Training Inductive Graph Neural Network for Large-scale Knowledge Graph Reasoning cites Composition-based Multi-Relational Graph Convolutional Networks
Cited by top-tier papers4
- Ultrahyperbolic Knowledge Graph EmbeddingsBo Xiong, Shichao Zhu, Mojtaba Nayyeri, Chengjin Xu et al.KDD 2022 · 32 citations
- Swift and Sure: Hardness-aware Contrastive Learning for Low-dimensional Knowledge Graph EmbeddingsKai Wang, Yu Liu, Quan Z. ShengWWW 2022 · 21 citations
- Complex Hyperbolic Knowledge Graph Embeddings with Fast Fourier TransformHuiru Xiao, Xin Liu, Yangqiu Song, Ginny Y. Wong et al.EMNLP 2022 · 9 citations
- TIGER: Training Inductive Graph Neural Network for Large-scale Knowledge Graph ReasoningKai Wang, Yuwei Xu, Siqiang LuoVLDB 2024 · 3 citations
Builds on7
- Composition-based Multi-Relational Graph Convolutional NetworksShikhar Vashishth, Soumya Sanyal, Vikram Nitin, Partha P. TalukdarICLR 2020 · 1,105 citations
- Hyperbolic Neural Networks++Ryohei Shimizu, Yusuke Mukuta, Tatsuya HaradaICLR 2021 · 791 citations
- Knowledge Association with Hyperbolic Knowledge Graph EmbeddingsZequn Sun, Muhao Chen, Wei Hu, Chengming Wang et al.EMNLP 2020 · 72 citations
- ReInceptionE: Relation-Aware Inception Network with Joint Local-Global Structural Information for Knowledge Graph EmbeddingZhiwen Xie, Guangyou Zhou, Jin Liu, Jimmy Xiangji HuangACL 2020 · 64 citations
- Low-Dimensional Hyperbolic Knowledge Graph EmbeddingsInes Chami, Adva Wolf, Da-Cheng Juan, Frederic Sala et al.ACL 2020 · 48 citations
Related papers
- Enhancing Hyperbolic Knowledge Graph Embeddings via Lorentz TransformationsXiran Fan, Minghua Xu, Huiyuan Chen, Yuzhong Chen et al.ACL Findings 2024 · 2 citations
- Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph EmbeddingYihua Zhu, Hidetoshi ShimodairaEMNLP Findings 2024 · 3 citations
- BiQUE: Biquaternionic Embeddings of Knowledge GraphsJia Guo, Stanley KokEMNLP 2021
- 5* Knowledge Graph Embeddings with Projective TransformationsMojtaba Nayyeri, Sahar Vahdati, Can Aykul, Jens LehmannAAAI 2021 · 39 citations
- MulDE: Multi-teacher Knowledge Distillation for Low-dimensional Knowledge Graph EmbeddingsKai Wang, Yu Liu, Qian Ma, Quan Z. ShengWWW 2021 · 67 citations
