AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Does Invariant Graph Learning via Environment Augmentation Learn Invariance?

Yongqiang Chen, Yatao Bian, Kaiwen Zhou, Binghui Xie, Bo Han, James Cheng

NeurIPS 2023 · Graph learning › Graph self-supervised learning · approach: Graph out-of-distribution generalization · 5 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 an environment assistant to split graphs by whether its proxy predictions are correct, then maximize cross-set intra-class subgraph mutual informationCIGA-style invariant graph learning · Two-piece graphs, {0.7,0.9}OOD accuracy: 43.62±3.20 -> 72.50±1.06Improved
Use an environment assistant and cross-set contrastive samplingCIGA-style invariant graph learning · Two-piece averageOOD accuracy: 67.18 -> 79.21Improved
Use an environment assistant and cross-set contrastive samplingCIGA-style invariant graph learning · EC50-Assay, EC50-Scaffold, EC50-Size, Ki-Assay, Ki-Scaffold, Ki-Size, CMNIST-sp, Graph-SST2OOD accuracy: 76.42±1.59 -> 77.56±2.88; 64.56±1.25 -> 66.28±0.45; 61.61±1.52 -> 64.25±1.21; 74.61±2.28 -> 77.92±2.48; 69.38±1.65 -> 73Improved
Add the CIGAv2 constraint to GALA (ablation)GALA · Ki-ScaffoldOOD performanceImproved
Add the CIGAv2 constraint to GALA (ablation)GALA · CMNIST-spOOD performanceNo clear effect
Set the contrastive penalty weight to zero (ablation)GALA · Two-piece {0.7,0.9}OOD performanceHurt
Set the positive/negative group upsampling times to zero (ablation)GALA · Two-piece {0.7,0.9}OOD performanceHurt
Vary the contrastive penalty weight or upsampling times away from zero (ablation)GALA · Two-piece {0.7,0.9}OOD performanceNo clear effect
Infer environment labels or generate virtual environments without ensuring faithful environment informationInvariant graph learning methods · Two-piece graphsOOD performanceHurt
Use GALA rather than CIGAInvariant graph learning · CMNIST-spOOD accuracy: 15.83±2.56 -> 68.94±0.56Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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