AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Understanding and Improving Knowledge Graph Embedding for Entity Alignment

Lingbing Guo, Qiang Zhang, Zequn Sun, Mingyang Chen, Wei Hu, Huajun Chen

ICML 2022 · Graph learning › Knowledge and temporal graphs · approach: Knowledge graph embeddings

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 NeoEA neural ontology alignmentBootEA, SEA, RSN, RDGCN · V1 datasets (EN-FR, EN-DE, D-W, D-Y)H@1 / MRRImproved
add NeoEA neural ontology alignmentSEA · V1 EN-FRMRR: 0.397 -> 0.443Improved
add NeoEA neural ontology alignmentRSN · V1 EN-FRH@1: 0.393 -> 0.399Improved
add conditional neural axioms (relation-conditioned triple and head/tail entity distributions) (ablation)RDGCN · V1 EN-FRH@1: 0.771 -> 0.775 (Partial to Full)Improved
align only the basic (unconditional) entity embedding distribution (ablation)RDGCN · V1 EN-FRH@1: 0.755 -> 0.755 (Original vs Basic)No clear effect
add conditional head/tail entity axioms on top of conditional triple axioms (ablation)RDGCN · V1 EN-FRH@1: 0.755 (Basic) -> 0.771 (Partial)Improved
add NeoEA on SEA (scalability test on OpenEA 100K)SEA · OpenEA 100K datasetstraining epoch timeNo clear effect
add NeoEA on SEA (overall training time)SEA · OpenEA 100K datasetsoverall training time: roughly doubledHurt

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