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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Seeking the equivalent entities among multi-source Knowledge Graphs (KGs) isthe pivotal step to KGs integration, also known as \emph{entity alignment}(EA). However, most existing EA methods are inefficient and poor inscalability. A recent summary points out that some of them even require severaldays to deal with a dataset containing 200,000 nodes (DWY100K). We believeover-complex graph encoder and inefficient negative sampling strategy are thetwo main reasons. In this paper, we propose a novel KG encoder -- DualAttention Matching Network (Dual-AMN), which not only models both intra-graphand cross-graph information smartly, but also greatly reduces computationalcomplexity. Furthermore, we propose the Normalized Hard Sample Mining Loss tosmoothly select hard negative samples with reduced loss shift. The experimentalresults on widely used public datasets indicate that our method achieves bothhigh accuracy and high efficiency. On DWY100K, the whole running process of ourmethod could be finished in 1,100 seconds, at least 10* faster than previouswork. The performances of our method also outperform previous works across alldatasets, where Hits@1 and MRR have been improved from 6% to 13%.

Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Mining