5* Knowledge Graph Embeddings with Projective Transformations
This addresses a limitation in knowledge graph completion for multi-relational graphs, offering a more flexible method to capture diverse subgraph structures.
The paper tackled the problem of link prediction in knowledge graphs with multiple subgraph structures by proposing a novel embedding model (5*E) in projective geometry that supports multiple simultaneous transformations, and it outperformed existing approaches on widely used benchmarks.
Performing link prediction using knowledge graph embedding models has become a popular approach for knowledge graph completion. Such models employ a transformation function that maps nodes via edges into a vector space in order to measure the likelihood of the links. While mapping the individual nodes, the structure of subgraphs is also transformed. Most of the embedding models designed in Euclidean geometry usually support a single transformation type - often translation or rotation, which is suitable for learning on graphs with small differences in neighboring subgraphs. However, multi-relational knowledge graphs often include multiple sub-graph structures in a neighborhood (e.g. combinations of path and loop structures), which current embedding models do not capture well. To tackle this problem, we propose a novel KGE model (5*E) in projective geometry, which supports multiple simultaneous transformations - specifically inversion, reflection, translation, rotation, and homothety. The model has several favorable theoretical properties and subsumes the existing approaches. It outperforms them on the most widely used link prediction benchmarks