English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent knowledge graph embedding (KGE) models based on hyperbolic geometryhave shown great potential in a low-dimensional embedding space. However, thenecessity of hyperbolic space in KGE is still questionable, because thecalculation based on hyperbolic geometry is much more complicated thanEuclidean operations. In this paper, based on the state-of-the-arthyperbolic-based model RotH, we develop two lightweight Euclidean-based models,called RotL and Rot2L. The RotL model simplifies the hyperbolic operationswhile keeping the flexible normalization effect. Utilizing a novel two-layerstacked transformation and based on RotL, the Rot2L model obtains an improvedrepresentation capability, yet costs fewer parameters and calculations thanRotH. The experiments on link prediction show that Rot2L achieves thestate-of-the-art performance on two widely-used datasets in low-dimensionalknowledge graph embeddings. Furthermore, RotL achieves similar performance asRotH but only requires half of the training time.

Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings