AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Logic Attention Based Neighborhood Aggregation for Inductive Knowledge Graph Embedding

Peifeng Wang, Jialong Han, Chenliang Li, Rong Pan

AAAI 2019 · Graph learning › Knowledge and temporal graphs · approach: Knowledge graph embeddings

Read the paper

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
use logic-rule and neural attention to weight neighbors instead of mean poolinginductive KG embedding · FB15K Subject-10MRR: 0.310 -> 0.394Improved
use logic-rule and neural attention to weight neighbors instead of mean poolinginductive KG embedding · FB15K Object-10MRR: 0.251 -> 0.314Improved
make neighbor attention query-relation aware (ablation)LAN on FB15K Subject-10 · FB15K Subject-10MRR: 0.331 -> 0.355Improved
add logic-rule attention to query-aware neural attention (ablation)LAN on FB15K Subject-10 · FB15K Subject-10MRR: 0.355 -> 0.394Improved
add neural attention to logic-rule-only weighting (ablation)LAN on FB15K Subject-10 · FB15K Subject-10MRR: 0.375 -> 0.394Improved
replace TransE scoring with Distmult (ablation)LAN on FB15K Subject-10 · FB15K Subject-10MRR: 0.394 -> 0.378Hurt

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