AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Knowledge Graph Alignment Network with Gated Multi-Hop Neighborhood Aggregation

Zequn Sun, Chengming Wang, Wei Hu, Muhao Chen, Jian Dai, Wei Zhang, Yuzhong Qu

AAAI 2020 · Graph learning › Knowledge and temporal graphs · approach: Knowledge graph embeddings · 363 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 neighborhood augmentation edges between pre-aligned counterparts (ablation)AliNet · DBP15K (DBP_ZH-EN, DBP_JA-EN, DBP_FR-EN) and DWY100K (DBP-WD, DBP-YG)Hits@1: 0.012-0.037Improved
Add relation loss (ablation)AliNet · DBP15K and DWY100KHits@1: 0.539 -> 0.525; 0.549 -> 0.539; 0.552 -> 0.535; 0.690 -> 0.679; 0.786 -> 0.773Improved
Aggregate two-hop neighbors in addition to one-hop neighbors (ablation)AliNet · DBP15KHits@1: 0.487 -> 0.539; 0.507 -> 0.549; 0.508 -> 0.552Improved
Replace gating with addition for combining hop representations (ablation)AliNet · DBP15KHits@1: 0.539 -> 0.498; 0.549 -> 0.515; 0.552 -> 0.501Hurt
Replace proposed attention with GAT attention (ablation)AliNet · DBP15KHits@1: 0.539 -> 0.517; 0.549 -> 0.531; 0.552 -> 0.523Hurt
Use GCN layers for mixed two-hop neighborhood aggregation (ablation)AliNet · DBP15KHits@1: 0.539 -> 0.227; 0.549 -> 0.294; 0.552 -> 0.258Hurt
Increase hop aggregation depth from two to three (ablation)AliNet · DBP15KHits@1: 0.539 -> 0.461; 0.549 -> 0.484; 0.552 -> 0.450Hurt
Increase hop aggregation depth from two to four (ablation)AliNet · DBP15KHits@1: 0.539 -> 0.386; 0.549 -> 0.407; 0.552 -> 0.373Hurt
Use three or four network layers instead of two (ablation)AliNet · DBP15KHits@1Hurt
Use combined representations from all layers rather than a layer-specific representation (ablation)AliNet · DBP15KHits@1Improved
Use distant neighbors to compensate for non-isomorphic direct neighborhoodsAliNet · DBP15Kone-hop neighbor overlap coefficientImproved

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