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

We propose an entity-agnostic representation learning method for handling theproblem of inefficient parameter storage costs brought by embedding knowledgegraphs. Conventional knowledge graph embedding methods map elements in aknowledge graph, including entities and relations, into continuous vectorspaces by assigning them one or multiple specific embeddings (i.e., vectorrepresentations). Thus the number of embedding parameters increases linearly asthe growth of knowledge graphs. In our proposed model, Entity-AgnosticRepresentation Learning (EARL), we only learn the embeddings for a small set ofentities and refer to them as reserved entities. To obtain the embeddings forthe full set of entities, we encode their distinguishable information fromtheir connected relations, k-nearest reserved entities, and multi-hopneighbors. We learn universal and entity-agnostic encoders for transformingdistinguishable information into entity embeddings. This approach allows ourproposed EARL to have a static, efficient, and lower parameter count thanconventional knowledge graph embedding methods. Experimental results show thatEARL uses fewer parameters and performs better on link prediction tasks thanbaselines, reflecting its parameter efficiency.

Entity-Agnostic Representation Learning for Parameter-Efficient Knowledge Graph Embedding