AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Uncovering the Structural Fairness in Graph Contrastive Learning

Ruijia Wang, Xiao Wang, Chuan Shi, Le Song

NeurIPS 2022 · Graph learning › Graph self-supervised learning · approach: Graph contrastive learning analysis · 19 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
Use GRADE instead of GCNnode classification models · CoraBias: 1.70 -> 0.48Improved
Use GRADE instead of GCNnode classification models · CiteseerBias: 1.85 -> 1.52Improved
Use GRADE instead of GCNnode classification models · PhotoBias: 0.28 -> 0.20Improved
Use GRADE instead of GCNnode classification models · ComputerBias: 0.50 -> 0.35Improved
Add random interpolation when augmenting tail-node neighborhoods (ablation)GRADE · CoraG. Mean: 90.86 -> 92.87Improved
Add random interpolation when augmenting tail-node neighborhoods (ablation)GRADE · CiteseerG. Mean: 84.96 -> 85.88Improved
Add random deleting when purifying head-node neighborhoods (ablation)GRADE · CoraG. Mean: 90.54 -> 92.87Improved
Add random deleting when purifying head-node neighborhoods (ablation)GRADE · CiteseerG. Mean: 84.21 -> 85.88Improved
Add random interpolation and random deleting (ablation)GRADE · CoraG. Mean: 89.97 -> 92.87Improved
Add random interpolation and random deleting (ablation)GRADE · CiteseerG. Mean: 83.00 -> 85.88Improved
Choose a suitable tail/head threshold rather than an overly small or large thresholdGRADE · CoraMicro-F1Mixed
Increase feature drop rate too farGRADE graph augmentation · CoraMicro-F1Hurt

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