A Semantic Partitioning Method for Large-Scale Training of Knowledge Graph Embeddings
This addresses the need for more semantic and scalable embeddings for knowledge graph tasks, but appears incremental as it builds on existing methods.
The paper tackles the problem of knowledge graph embeddings lacking semantic information and scalability by incorporating ontology and partitioning based on classes, achieving good performance on popular benchmarks.
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.