AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learning

Hidetaka Kamigaito, Katsuhiko Hayashi

ICML 2022 · Graph learning › Knowledge and temporal graphs · approach: Knowledge graph embeddings · 9 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
Add Uniq subsampling (ablation)HAKE · FB15k-237MRR: 32.3 -> 35.4Improved
Add Freq subsampling (ablation)HAKE · FB15k-237MRR: 32.3 -> 34.9Improved
Replace Base subsampling with Uniq subsampling (ablation)HAKE · FB15k-237MRR: 34.5 -> 35.4Improved
Add Uniq subsampling (ablation)HAKE · WN18RRMRR: 49.1 -> 49.8Improved
Replace Base subsampling with Uniq subsampling (ablation)HAKE · WN18RRMRR: 49.8 -> 49.8No clear effect
Add Uniq subsampling (ablation)HAKE · YAGO3-10MRR: 53.4 -> 55.0Improved
Replace Base subsampling with Freq subsampling (ablation)HAKE · YAGO3-10MRR: 54.3 -> 54.0Hurt
Increase the margin for TransE and RotatE (ablation)Distance-based KGE models · FB15k-237 and WN18RRMRRImproved
Set a non-zero margin (ablation)RESCAL, ComplEx, and DistMult · FB15k-237 and WN18RRMRRNo clear effect
Increase negative sample count (ablation)TransE and RotatE with original NS loss · FB15k-237MRRImproved
Increase negative sample count (ablation)RESCAL, ComplEx, and DistMult with original NS loss · FB15k-237 and WN18RRMRRNo clear effect
Use the NS loss normalized by the number of negative samples (ablation)KGE models · FB15k-237 and WN18RRMRRMixed

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