AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

GraphDE: A Generative Framework for Debiased Learning and Out-of-Distribution Detection on Graphs

Zenan Li, Qitian Wu, Fan Nie, Junchi Yan

NeurIPS 2022 · Graph learning › Graph self-supervised learning · approach: Graph out-of-distribution generalization · 8 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 GraphDE-a to TopKPool backboneTopKPool · SPMotif debiasingtest accuracy (%): 78.43 -> 88.54Improved
GraphDE-a versus strongest baseline GRANDTopKPool · SPMotif debiasingtest accuracy (%): 83.25 -> 88.54Improved
add GRAND to GAT backboneGAT · SPMotif debiasingtest accuracy (%): 65.02 -> 65.27No clear effect
add DropEdge to GCN backboneGCN · SPMotif debiasingtest accuracy (%): 68.67 -> 65.59Hurt
use EM-based GraphDE-a instead of variational GraphDE-vGraphDE · SPMotif debiasing, TopKPooltest accuracy (%): 85.11 -> 88.54Improved
GraphDE detector versus strongest baseline on MNIST-75spGLocalKD · MNIST-75sp OOD detectionAUROC (%): 86.22 -> 95.53Improved
GraphDE versus MSP on MNIST-75spMSP · MNIST-75sp OOD detectionAUROC (%): 62.37 -> 95.53Improved
GraphDE versus GLocalKD on DrugOODGLocalKD · DrugOOD OOD detectionFPR95 (%): 70.28 -> 80.30Hurt
GraphDE versus OCGIN on CollabOCGIN · Collab OOD detectionFPR95 (%): 86.70 -> 64.40Improved
remove L_reg (structure estimation model) (ablation)GraphDE-a · Collab debiasingtest accuracy: over 6% drop at biased ratio 0.25Hurt
remove L_cls (classification model) (ablation)GraphDE-a · Collab OOD detectionAUROC: approximately 3% gap at biased ratio 0.3Hurt
raise prior ratio above 0.7 (ablation)GraphDE · Collab debiasingtest accuracyHurt

Later papers that compared with this method

1 later accepted paper reports GraphDE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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