AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

On Completing Sparse Knowledge Base with Transitive Relation Embedding

AAAI 2019 · Graph learning › Knowledge and temporal graphs · approach: Knowledge graph embeddings · 11 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add TRE transitive relation patterns to baseline embedding scoresTransE · FB15K tail predictionMRR: .2371 -> .5444Helped
add TRE to baselineComplEx · WN18 tail predictionMRR: .5627 -> .6351Helped
add TRE to baselineTransE · DBP relation prediction (sparse)MRR: .0121 -> .1827Helped
add TRE to baselineComplEx · FB15K relation predictionMRR: .4442 -> .6591Helped
add TRE to baselineComplEx · WN18 relation predictionMRR: .9493 -> .9016Hurt
TRE alone vs baselines on sparse FB15K subsetTRE · Sparse FB15K relation predictionMRR: .4488 -> .6429Helped
learn relation embeddings only (no entity embeddings)TRE · training timeapprox. execution time (s): 400 -> 360Helped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy