EMNLP Findings2024
Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding
Yihua Zhu, Hidetoshi Shimodaira
摘要
The primary aim of Knowledge Graph Embeddings (KGE) is to learn low-dimensional representations of entities and relations for predicting missing facts. Although rotation-based methods like RotatE (Sun et al., 2019) and QuatE (Zhang et al., 2019) perform well in KGE, they face two challenges: limited model flexibility requiring proportional increases in relation size with entity dimension, and difficulties in generalizing the model for higherdimensional rotations. To address these issues, we introduce OrthogonalE, a novel KGE model employing matrices for entities and block-diagonal orthogonal matrices with Riemannian optimization for relations. This approach not only enhances the generality and flexibility of KGE models but also captures several relation patterns that rotation-based methods can identify. Experimental results indicate that our new KGE model, OrthogonalE, offers generality and flexibility, captures several relation patterns, and significantly outperforms state-of-the-art KGE models while substantially reducing the number of relation parameters.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
脉络
它引用的 Paper6
- HittER: Hierarchical Transformers for Knowledge Graph EmbeddingsSanxing Chen, Xiaodong Liu, Jianfeng Gao, Jian Jiao 等EMNLP 2021 · 110 次引用
- Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph EmbeddingYun Tang, Jing Huang, Guangtao Wang, Xiaodong He 等ACL 2020 · 92 次引用
- Unsupervised Learning of Equivariant Structure from SequencesTakeru Miyato, Masanori Koyama, Kenji FukumizuNeurIPS 2022 · 17 次引用
- Coordinate Descent on the Orthogonal Group for Recurrent Neural Network TrainingEstelle M. Massart, Vinayak AbrolAAAI 2022 · 13 次引用
- Generalizing Knowledge Graph Embedding with Universal Orthogonal ParameterizationRui Li, Chaozhuo Li, Yanming Shen, Zeyu Zhang 等ICML 2024 · 11 次引用
相关 Paper
- HousE: Knowledge Graph Embedding with Householder ParameterizationRui Li, Jianan Zhao, Chaozhuo Li, Di He 等ICML 2022 · 66 次引用
- Dual Quaternion Knowledge Graph EmbeddingsZongsheng Cao, Qianqian Xu, Zhiyong Yang, Xiaochun Cao 等AAAI 2021 · 186 次引用
- Improving Knowledge Graph Embedding Using Affine Transformations of Entities Corresponding to Each RelationJinfa Yang, Yongjie Shi, Xin Tong, Robin Wang 等EMNLP Findings 2021 · 5 次引用
- Enhancing Hyperbolic Knowledge Graph Embeddings via Lorentz TransformationsXiran Fan, Minghua Xu, Huiyuan Chen, Yuzhong Chen 等ACL Findings 2024 · 2 次引用
- BiQUE: Biquaternionic Embeddings of Knowledge GraphsJia Guo, Stanley KokEMNLP 2021
