AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Graph Generative Model for Benchmarking Graph Neural Networks

Minji Yoon, Yue Wu, John Palowitch, Bryan Perozzi, Russ Salakhutdinov

ICML 2023 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation · 2 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
Remove label conditioning from CGT (ablation)CGT · Cora, Citeseer, Pubmed (9 GNNs)Pearson: 0.943 vs 0.592 without labelImproved
Add layer-based position embeddings (ablation)CGT · Cora, Citeseer, Pubmed (9 GNNs)Pearson: 0.943 vs 0.411 withoutImproved
Add ancestor-only attention masks (ablation)CGT · Cora, Citeseer, Pubmed (9 GNNs)Pearson: 0.943 vs 0.329 withoutImproved
Add all three modules (label, position, attention) vs plain Transformer (ablation)CGT · Cora, Citeseer, Pubmed (9 GNNs)MSE: 0.017 vs 0.034Improved
Apply k-anonymity (k=100 to 1000) during quantization (ablation)CGT · Cora, GNN benchmark correlationPearson: 0.934 no privacy -> 0.916 (k=100), 0.862 (k=500), 0.030 (k=1000)Hurt
Use DP-SGD to train the transformer for edge distributions (ablation)CGT · Cora, GNN benchmark correlationPearson: 0.112 at eps=1e6 vs 0.934 no privacy; 0.890 only at eps=1e9Hurt
Apply DP k-means (eps=1, delta=0.01) for node attribute privacy (ablation)CGT · Cora, GNN benchmark correlationPearson: 0.874 (eps=1) vs 0.934 no privacyNo clear effect
Replace privacy method with edge addition, deletion, or attribute noise baselinesGNN benchmark MSE on Cora · Cora, 4 GNNsMSE: K-anonymity K=5 MSE 0.001 with 20% re-identification; noise-based variants range 0.021 to 0.548Mixed
CGT vs baselines (VGAE, GraphVAE, GraphAF, GraphDF, GraphEBM)benchmark effectiveness · 7 public graph datasets, 9 GNNsMSE and Pearson/Spearman: up to 33% lower MSE, 0.80 higher Pearson, 1.03 higher SpearmanImproved
Scale CGT to ogbn-arxiv and ogbn-products via computation graph samplingCGT · ogbn-arxiv, ogbn-productsPearson: Pearson 0.989; training 1.1 hr (arxiv), 14.7 hr (products)Improved

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