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

Knowledge graph (KG) embedding methods which map entities and relations tounique embeddings in the KG have shown promising results on many reasoningtasks. However, the same embedding dimension for both dense entities and sparseentities will cause either over parameterization (sparse entities) or underfitting (dense entities). Normally, a large dimension is set to get betterperformance. Meanwhile, the inference time grows log-linearly with the numberof entities for all entities are traversed and compared. Both the parameter andinference become challenges when working with huge amounts of entities. Thus,we propose PIE, a \textbf{p}arameter and \textbf{i}nference \textbf{e}fficientsolution. Inspired from tensor decomposition methods, we find that decomposeentity embedding matrix into low rank matrices can reduce more than half of theparameters while maintaining comparable performance. To accelerate modelinference, we propose a self-supervised auxiliary task, which can be seen asfine-grained entity typing. By randomly masking and recovering entities'connected relations, the task learns the co-occurrence of entity and relations.Utilizing the fine grained typing, we can filter unrelated entities duringinference and get targets with possibly sub-linear time requirement.Experiments on link prediction benchmarks demonstrate the proposed keycapabilities. Moreover, we prove effectiveness of the proposed solution on theOpen Graph Benchmark large scale challenge dataset WikiKG90Mv2 and achieve thestate of the art performance.

PIE: a Parameter and Inference Efficient Solution for Large Scale Knowledge Graph Embedding Reasoning