Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding

• URL: http://arxiv.org/abs/2401.05967v3
• Date: Wed, 02 Oct 2024 04:17:36 GMT
• Title: Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding
• Authors: Yihua Zhu, Hidetoshi Shimodaira,
• Abstract summary: A Knowledge Graph embeddings (KGE) is to learn low-dimensional representations of entities and relations for predicting missing facts. We introduce OrthogonalE, a novel KGE model employing matrices for entities and block-diagonal matrices for relations. The experimental results indicate that our new KGE model, OrthogonalE, is both general and flexible, significantly outperforming state-of-the-art KGE models.
• Score: 5.463034010805521
• License:
• Abstract: The primary aim of Knowledge Graph embeddings (KGE) is to learn low-dimensional representations of entities and relations for predicting missing facts. While rotation-based methods like RotatE and QuatE 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 higher-dimensional 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 enhances the generality and flexibility of KGE models. The experimental results indicate that our new KGE model, OrthogonalE, is both general and flexible, significantly outperforming state-of-the-art KGE models while substantially reducing the number of relation parameters.

Related papers

• Knowledge Graph Embeddings: A Comprehensive Survey on Capturing Relation Properties [5.651919225343915]
  Knowledge Graph Embedding (KGE) techniques play a pivotal role in transforming symbolic Knowledge Graphs into numerical representations. This paper addresses the complex mapping properties inherent in relations, such as one-to-one, one-to-many, many-to-one, and many-to-many mappings. We explore innovative ideas such as integrating multimodal information into KGE, enhancing relation pattern modeling with rules, and developing models to capture relation characteristics in dynamic KGE settings.
  arXiv  Detail & Related papers  (2024-10-16T08:54:52Z)
• A Comprehensive Study on Knowledge Graph Embedding over Relational Patterns Based on Rule Learning [49.09125100268454]
  Knowledge Graph Embedding (KGE) has proven to be an effective approach to solving the Knowledge Completion Graph (KGC) task. Relational patterns are an important factor in the performance of KGE models. We introduce a training-free method to enhance KGE models' performance over various relational patterns.
  arXiv  Detail & Related papers  (2023-08-15T17:30:57Z)
• Scaling Pre-trained Language Models to Deeper via Parameter-efficient Architecture [68.13678918660872]
  We design a more capable parameter-sharing architecture based on matrix product operator (MPO) MPO decomposition can reorganize and factorize the information of a parameter matrix into two parts. Our architecture shares the central tensor across all layers for reducing the model size.
  arXiv  Detail & Related papers  (2023-03-27T02:34:09Z)
• Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure [36.507635518425744]
  We propose a knowledge graph contrastive learning framework based on relation-symmetrical structure, KGE-SymCL. Our framework mines symmetrical structure information in KGs to enhance the discriminative ability of KGE models.
  arXiv  Detail & Related papers  (2022-11-19T16:30:29Z)
• Learning Graphical Factor Models with Riemannian Optimization [70.13748170371889]
  This paper proposes a flexible algorithmic framework for graph learning under low-rank structural constraints. The problem is expressed as penalized maximum likelihood estimation of an elliptical distribution. We leverage geometries of positive definite matrices and positive semi-definite matrices of fixed rank that are well suited to elliptical models.
  arXiv  Detail & Related papers  (2022-10-21T13:19:45Z)
• ProjB: An Improved Bilinear Biased ProjE model for Knowledge Graph Completion [1.5576879053213302]
  This work improves on ProjE KGE due to low computational complexity and high potential for model improvement. Experimental results on benchmark Knowledge Graphs (KGs) such as FB15K and WN18 show that the proposed approach outperforms the state-of-the-art models in entity prediction task.
  arXiv  Detail & Related papers  (2022-08-15T18:18:05Z)
• Rethinking Graph Convolutional Networks in Knowledge Graph Completion [83.25075514036183]
  Graph convolutional networks (GCNs) have been increasingly popular in knowledge graph completion (KGC) In this paper, we build upon representative GCN-based KGC models and introduce variants to find which factor of GCNs is critical in KGC. We propose a simple yet effective framework named LTE-KGE, which equips existing KGE models with linearly transformed entity embeddings.
  arXiv  Detail & Related papers  (2022-02-08T11:36:18Z)
• ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs [73.86041481470261]
  Cone Embeddings (ConE) is the first geometry-based query embedding model that can handle conjunction, disjunction, and negation. ConE significantly outperforms existing state-of-the-art methods on benchmark datasets.
  arXiv  Detail & Related papers  (2021-10-26T14:04:02Z)
• BiQUE: Biquaternionic Embeddings of Knowledge Graphs [9.107095800991333]
  Existing knowledge graph embeddings (KGEs) compactly encode multi-relational knowledge graphs (KGs) It is crucial for KGE models to unify multiple geometric transformations so as to fully cover the multifarious relations in KGs. We propose BiQUE, a novel model that employs biquaternions to integrate multiple geometric transformations.
  arXiv  Detail & Related papers  (2021-09-29T13:05:32Z)
• Self-supervised Geometric Perception [96.89966337518854]
  Self-supervised geometric perception is a framework to learn a feature descriptor for correspondence matching without any ground-truth geometric model labels. We show that SGP achieves state-of-the-art performance that is on-par or superior to the supervised oracles trained using ground-truth labels.
  arXiv  Detail & Related papers  (2021-03-04T15:34:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.