AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Type-Aware Anchor Link Prediction across Heterogeneous Networks Based on Graph Attention Network

Xiaoxue Li, Yanmin Shang, Yanan Cao, Yangxi Li, Jianlong Tan, Yanbing Liu

AAAI 2020 · Graph learning › Graph self-supervised learning · approach: Heterophily and imbalance on graphs · 60 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 type-aware matching to fusion-only alignment (TALPf -> TALP) (ablation)TALP · Twitter-FoursquareP@1 (%): 42.66 -> 43.79Improved
add type-aware matching to fusion-only alignment (TALPf -> TALP) (ablation)TALP · Aminer-MagMAP@30 (%): 66.25 -> 82.39Improved
add fusion-vector matching to type-aware-only alignment (TALPa -> TALP) (ablation)TALP · Twitter-FoursquareMAP@30 (%): 57.68 -> 59.33Improved
add fusion-vector matching to type-aware-only alignment (TALPa -> TALP) (ablation)TALP · Aminer-MagMAP@30 (%): 79.49 -> 82.39Improved
use type-aware only instead of fusion only (ablation)TALP · Aminer-MagMAP@30 (%): 66.25 -> 79.49Improved
replace HAN/PME/HHNE-style fusion embedding with TALP's GAT fusion (TALPf vs PME)TALPf · Aminer-MagP@1 (%): 45.91 -> 50.56Improved
use TALP instead of strongest baseline PMETALP · Aminer-MagMAP@30 (%): 55.96 -> 82.39Improved
use TALP instead of strongest baseline PMETALP · Twitter-FoursquareMAP@30 (%): 52.42 -> 59.33Improved
set type-aware weight (1-omega) to 0 (fusion only) (ablation)TALP · Twitter-Foursquare and Aminer-MagP@k / MAPHurt
increase type-aware weight (1-omega) beyond optimum (ablation)TALP · Twitter-Foursquare and Aminer-MagP@k / MAPMixed
increase attention heads K beyond 3 (ablation)TALP · Twitter-Foursquare and Aminer-MagP@k / MAPHurt

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