AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Bringing Light Into the Dark: A Large-Scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework

Mehdi Ali, Max Berrendorf, Charles Tapley Hoyt, Laurent Vermue, Mikhail Galkin, Sahand Sharifzadeh, Asja Fischer, Volker Tresp C, Jens Lehmann

TPAMI 2021 · Graph learning › Knowledge and temporal graphs · approach: Knowledge graph embeddings · 169 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
tune configuration (loss, training approach, inverse relations) with large HPORotatE · WN18RRhits@10: 56.61% -> 60.09%Improved
tune configuration with large HPOMuRE · WN18RRhits@10: 55.50% -> 57.90%Improved
tune configuration with large HPOConvE · WN18RRhits@10: 52.00% -> 56.33%Improved
tune configuration with large HPOTuckER · WN18RRhits@10: 52.6% -> 56.09%Improved
train with Adam instead of AdadeltaKGEMs · Kinshipshits@10Improved
train TransE for 4000 epochs instead of 1000TransE · WN18reproduction: 1000 -> 4000 epochsImproved
use LCWA instead of sLCWA with BCEL/SPL (ablation)KGEMs · WN18RRhits@10Mixed
use LCWA instead of sLCWA (ablation)TransH · WN18RRhits@10Hurt
use LCWA instead of sLCWA (ablation)RotatE · WN18RRhits@10Improved
explicitly model inverse relations (ablation)KGEMs · Kinshipshits@10 varianceImproved
use SPL instead of BCEL (ablation)KGEMs · WN18RRhits@10 varianceImproved
increase model sizeKGEMs · Kinshipshits@10No clear effect

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