AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

From Canonical Correlation Analysis to Self-supervised Graph Neural Networks

Hengrui Zhang, Qitian Wu, Junchi Yan, David Wipf, Philip S. Yu

NeurIPS 2021 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Contrastive versus non-contrastive theory · 49 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 CCA-SSG instead of MVGRLself-supervised node representation learning · Coratest accuracy: 83.5 ± 0.4 -> 84.2 ± 0.4Improved
Use CCA-SSG instead of MVGRLself-supervised node representation learning · Citeseertest accuracy: 73.3 ± 0.5 -> 73.1 ± 0.3No clear effect
Use CCA-SSG instead of GRACEself-supervised node representation learning · Pubmedtest accuracy: 80.6 ± 0.4 -> 81.6 ± 0.4Improved
Use CCA-SSG instead of GCAself-supervised node representation learning · Amazon Computertest accuracy: 87.85 ± 0.31 -> 88.74 ± 0.28Improved
Use CCA-SSG instead of GCAself-supervised node representation learning · Amazon Phototest accuracy: 92.49 ± 0.09 -> 93.14 ± 0.14Improved
Use CCA-SSG instead of GCAself-supervised node representation learning · Coauthor CStest accuracy: 93.10 ± 0.01 -> 93.31 ± 0.22Improved
Use CCA-SSG instead of GCAself-supervised node representation learning · Coauthor Physicstest accuracy: 95.68 ± 0.05 -> 95.38 ± 0.06No clear effect
Remove the invariance term (ablation)CCA-SSG · node classification benchmarkstest accuracyHurt
Add the invariance term (ablation)CCA-SSG without the invariance term · node classification benchmarkstest accuracyImproved
Remove the decorrelation term (ablation)CCA-SSG · node classification benchmarkstest accuracyHurt
Add the decorrelation term (ablation)CCA-SSG without the decorrelation term · node classification benchmarkstest accuracyImproved
Increase the decorrelation weight from too small to a suitable value (ablation)CCA-SSG · Cora, Citeseer, Pubmedtest accuracyImproved

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