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 embedding aims to predict the missing relations betweenentities in knowledge graphs. Tensor-decomposition-based models, such asComplEx, provide a good trade-off between efficiency and expressiveness, thatis crucial because of the large size of real world knowledge graphs. The recentmulti-partition embedding interaction (MEI) model subsumes these models byusing the block term tensor format and provides a systematic solution for thetrade-off. However, MEI has several drawbacks, some of which carried from itssubsumed tensor-decomposition-based models. In this paper, we address thesedrawbacks and introduce the Multi-partition Embedding Interaction iMprovedbeyond block term format (MEIM) model, with independent core tensor forensemble effects and soft orthogonality for max-rank mapping, in addition tomulti-partition embedding. MEIM improves expressiveness while still beinghighly efficient, helping it to outperform strong baselines and achievestate-of-the-art results on difficult link prediction benchmarks using fairlysmall embedding sizes. The source code is released athttps://github.com/tranhungnghiep/MEIM-KGE.

MEIM: Multi-partition Embedding Interaction Beyond Block Term Format for Efficient and Expressive Link Prediction