AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Generative Subgraph Contrast for Self-Supervised Graph Representation Learning

Yuehui Han, Le Hui, Haobo Jiang, Jianjun Qian, Jin Xie

ECCV 2022 · Graph learning › Graph self-supervised learning · approach: Contrastive learning with negatives and views · 23 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 OT distance contrastive loss instead of readout similarity (ablation)GSC · Coraaccuracy: 83.6 -> 84.6Improved
add OT distance contrastive loss instead of readout similarity (ablation)GSC · Citeseeraccuracy: 72 -> 73.7Improved
add OT distance contrastive loss instead of readout similarity (ablation)GSC · Pubmedaccuracy: 78.5 -> 82.1Improved
add subgraph generation module instead of perturbation (ablation)GSC · Coraaccuracy: 84.1 -> 84.6Improved
add subgraph generation module instead of perturbation (ablation)GSC · Citeseeraccuracy: 72.3 -> 73.7Improved
add subgraph generation module instead of perturbation (ablation)GSC · Pubmedaccuracy: 80.4 -> 82.1Improved
use BFS subgraph sampling instead of importance score (ablation)GSC · Coraaccuracy: 83.5 -> 84.6Improved
use BFS subgraph sampling instead of importance score (ablation)GSC · Citeseeraccuracy: 71.68 -> 73.7Improved
use BFS subgraph sampling instead of importance score (ablation)GSC · Pubmedaccuracy: 80.6 -> 82.1Improved
use BFS subgraph sampling instead of random walk (ablation)GSC · Coraaccuracy: 84.2 -> 84.6Improved
use BFS subgraph sampling instead of random walk (ablation)GSC · Citeseeraccuracy: 72.4 -> 73.7Improved
use BFS subgraph sampling instead of random walk (ablation)GSC · Pubmedaccuracy: 81.2 -> 82.1Improved

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