AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Contrastive Laplacian Eigenmaps

Hao Zhu, Ke Sun, Piotr Koniusz

NeurIPS 2021 · Graph learning › Graph self-supervised learning · approach: Contrastive learning with negatives and views · 22 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 COLES-S²GC instead of S²GCS²GC · Cora (5 labeled samples/class)accuracy (%): 71.4±4.4 -> 76.5±2.6Improved
use COLES-S²GC instead of S²GCS²GC · Citeseer (5 labeled samples/class)accuracy (%): 60.3±4.0 -> 67.5±2.2Improved
use COLES-S²GC instead of S²GCS²GC · Cora Full (5 labeled samples/class)accuracy (%): 41.8±1.7 -> 50.8±1.4Improved
use COLES-S²GC instead of S²GCS²GC · Ogbn-arxivtest accuracy (%): 72.01±0.25 -> 72.48±0.25Improved
remove negative Laplacian graphs (κ=0) (ablation)COLES-S²GC · Cora (5 labeled samples/class)accuracy (%): 76.24 -> 70.12Hurt
add more than one negative Laplacian graph (ablation)COLES-S²GC · Cora (5 labeled samples/class)accuracy (%): 76.24 -> 75.89 -> 75.79No clear effect
remove negative Laplacian graphs (κ=0) (ablation)COLES-GCN · Citeseer (5 labeled samples/class)accuracy (%): 65.85 -> 45.31Hurt
replace the geometric mean with the arithmetic mean in the uniformity loss (ablation)COLES-S²GC · Cora (5 labeled samples/class)accuracy (%): 76.5±2.6 -> 71.8±3.0Hurt
replace the geometric mean with the harmonic mean in the uniformity loss (ablation)COLES-S²GC · Cora (5 labeled samples/class)accuracy (%): 76.5±2.6 -> 75.2±3.5Hurt
replace the geometric mean with the quadratic mean in the uniformity loss (ablation)COLES-S²GC · Cora (5 labeled samples/class)accuracy (%): 76.5±2.6 -> 72.3±2.5Hurt
use Stiefel optimization instead of soft orthogonality (ablation)COLES-GCN · Cora (5 labeled samples/class)accuracy (%): 73.8±3.4 -> 75.0±3.4Improved
add data augmentation (ablation)COLES-GCN · Cora (5 labeled samples/class)accuracy (%): 73.8±3.4 -> 75.3±3.3Improved

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