A Semantic Partitioning Method for Large-Scale Training of Knowledge Graph Embeddings

TL;DR

This paper introduces a semantic partitioning method for large-scale knowledge graph embedding training that incorporates ontology information and class-based partitioning to enhance semantic richness and scalability.

Contribution

The paper proposes a novel algorithm that integrates ontology data and class-based partitioning to improve semantic content and enable large-scale training of knowledge graph embeddings.

Findings

Performs well on several popular benchmarks.

Enhances semantic information in embeddings.

Supports parallel training for large-scale graphs.

Abstract

In recent years, knowledge graph embeddings have achieved great success. Many methods have been proposed and achieved state-of-the-art results in various tasks. However, most of the current methods present one or more of the following problems: (i) They only consider fact triplets, while ignoring the ontology information of knowledge graphs. (ii) The obtained embeddings do not contain much semantic information. Therefore, using these embeddings for semantic tasks is problematic. (iii) They do not enable large-scale training. In this paper, we propose a new algorithm that incorporates the ontology of knowledge graphs and partitions the knowledge graph based on classes to include more semantic information for parallel training of large-scale knowledge graph embeddings. Our preliminary results show that our algorithm performs well on several popular benchmarks.