• Home
  • Search
  • Support and Centrality: Learning Weights for Knowledge Graph Embedding Models
  • Cite Icon16
  • https://doi.org/10.1007/978-3-030-03667-6_14Copy DOI Icon

Support and Centrality: Learning Weights for Knowledge Graph Embedding Models

  • Jan 1, 2018
  • Gengchen Mai +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Computing knowledge graph (KG) embeddings is a technique to learn distributional representations for components of a knowledge graph while preserving structural information. The learned embeddings can be used in multiple downstream tasks such as question answering, information extraction, query expansion, semantic similarity, and information retrieval. Over the past years, multiple embedding techniques have been proposed based on different underlying assumptions. The most actively researched models are translation-based which treat relations as translation operations in a shared (or relation-specific) space. Interestingly, almost all KG embedding models treat each triple equally, regardless of the fact that the contribution of each triple to the global information content differs substantially. Many triples can be inferred from others, while some triples are the foundational (basis) statements that constitute a knowledge graph, thereby supporting other triples. Hence, in order to learn a suitable embedding model, each triple should be treated differently with respect to its information content. Here, we propose a data-driven approach to measure the information content of each triple with respect to the whole knowledge graph by using rule mining and PageRank. We show how to compute triple-specific weights to improve the performance of three KG embedding models (TransE, TransR and HolE). Link prediction tasks on two standard datasets, FB15K and WN18, show the effectiveness of our weighted KG embedding model over other more complex models. In fact, for FB15K our TransE-RW embeddings model outperforms models such as TransE, TransM, TransH, and TransR by at least 12.98% for measuring the Mean Rank and at least 1.45% for HIT@10. Our HolE-RW model also outperforms HolE and ComplEx by at least 14.3% for MRR and about 30.4% for HIT@1 on FB15K. Finally, TransR-RW show an improvement over TransR by 3.90% for Mean Rank and 0.87% for HIT@10.

Similar Papers
  • PDF
  • Research Article
  • Citations6

Hyperplane-based time-aware knowledge graph embedding for temporal knowledge graph completion

  • Apr 28, 2022
  • Journal of Intelligent & Fuzzy Systems
  • Peng He +4
  • Book Chapter
  • Citations85

Temporal Knowledge Graph Completion Based on Time Series Gaussian Embedding

  • Jan 01, 2020
  • Chenjin Xu +4
  • Conference Article
  • Citations1

Understanding the Embedding Models on Hyper-relational Knowledge Graph

  • Nov 10, 2025
  • Yubo Wang +6
  • Video Transcripts

Sequence-to-Sequence Knowledge Graph Completion and Question Answering

  • May 07, 2022
  • Underline Science Inc.
  • Rainer Gemulla +2
  • Conference Article

FedAdap: An Adaptive Federated Knowledge Graph Embedding Framework for Tackling KGs Heterogeneity via Partial Model Sharing

  • Jun 30, 2025
  • Zihao Zheng +3
  • Video Transcripts

Poisoning Knowledge Graph Embeddings via Relation Inference Patterns

  • Aug 01, 2021
  • Underline Science Inc.
  • Peru Bhardwaj +3
  • Research Article
  • Citations3

A lightweight CNN-based knowledge graph embedding model with channel attention for link prediction.

  • Jan 01, 2023
  • Mathematical Biosciences and Engineering
  • Xin Zhou +4
  • PDF
  • Research Article
  • Citations7

On Training Knowledge Graph Embedding Models

  • Mar 31, 2021
  • Information
  • Sameh K Mohamed +2
  • PDF
  • Research Article
  • Citations15

A neuro-symbolic system over knowledge graphs for link prediction

  • Oct 04, 2024
  • Semantic Web
  • Ariam Rivas +3
  • PDF
  • Conference Article
  • Citations88

Knowledge Graph Embedding with Hierarchical Relation Structure

  • Jan 01, 2018
  • Zhao Zhang +4
  • Conference Article
  • Citations274

Co-training Embeddings of Knowledge Graphs and Entity Descriptions for Cross-lingual Entity Alignment

  • Jul 01, 2018
  • Muhao Chen +4
  • Research Article
  • Citations18

Analogical Inference Enhanced Knowledge Graph Embedding

  • Jun 26, 2023
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Zhen Yao +5
  • Conference Article
  • Citations3

Cycle or Minkowski

  • Oct 26, 2021
  • Han Yang +4
  • Book Chapter
  • Citations6

LightCAKE: A Lightweight Framework for Context-Aware Knowledge Graph Embedding

  • Jan 01, 2021
  • Zhiyuan Ning +4
  • Research Article
  • Citations19

CTEA: Context and Topic Enhanced Entity Alignment for knowledge graphs

  • Jun 19, 2020
  • Neurocomputing
  • Zhihuan Yan +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.