Knowledge Association with Hyperbolic Knowledge Graph Embeddings
This work addresses the problem of hierarchical structures and scalability in knowledge graphs for NLP applications, representing an incremental improvement over Euclidean embedding methods.
The paper tackled the challenge of capturing associations in knowledge graphs by proposing a hyperbolic relational graph neural network, which achieved effectiveness and efficiency in entity alignment and type inference tasks.
Capturing associations for knowledge graphs (KGs) through entity alignment, entity type inference and other related tasks benefits NLP applications with comprehensive knowledge representations. Recent related methods built on Euclidean embeddings are challenged by the hierarchical structures and different scales of KGs. They also depend on high embedding dimensions to realize enough expressiveness. Differently, we explore with low-dimensional hyperbolic embeddings for knowledge association. We propose a hyperbolic relational graph neural network for KG embedding and capture knowledge associations with a hyperbolic transformation. Extensive experiments on entity alignment and type inference demonstrate the effectiveness and efficiency of our method.