Hyperbolic Embedding

AbstractKnowledge graph (KG) embeddings learn low- dimensional representations of entities and relations to predict missing facts. KGs often exhibit hierarchical and logical patterns which must be preserved in the embedding …...

AbstractMatching equivalent entities across Knowledge graphs is a pivotal step for knowledge fusion. Previous approaches usually study the problem in Euclidean space. However, recent works have shown that hyperbolic space …...

AbstractRecent years have witnessed increasing interests in prompt-based learning in which models can be trained on only a few annotated instances, making them suitable in low-resource settings. It is even …...