AI Paper Atlas

Research map / Graph learning / GNN architectures

Information Obfuscation of Graph Neural Networks

Peiyuan Liao, Han Zhao, Keyulu Xu, Tommi Jaakkola, Geoffrey J. Gordon, Stefanie Jegelka, Ruslan Salakhutdinov

ICML 2021 · Graph learning › GNN architectures · approach: Graph structure learning · 7 citations (OpenAlex)

Read the paper

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
Train ChebNet with GAL using the Wasserstein objective at λ=0.5 rather than the Bose and Hamilton baselineChebNet on Movielens-1M · Movielens-1MGender-F1: 0.667 -> 0.593Improved
Train ChebNet with GAL using the Wasserstein objective at λ=0.5 rather than the Bose and Hamilton baselineChebNet on Movielens-1M · Movielens-1MRMSE: 0.874 -> 0.872Improved
Use the Wasserstein objective instead of Total VariationGCN on CiteSeer · CiteSeerMacro-F1: 0.785 -> 0.644Improved
Use the Wasserstein objective instead of Total VariationGCN on CiteSeer · CiteSeerAUC: 0.867 -> 0.814Hurt
Increase λ from 0 to 0.5 (ablation)ChebNet-TV on Movielens-1M · Movielens-1MGender-F1: 0.692 -> 0.617Improved
Increase λ from 0 to 0.5 (ablation)ChebNet-TV on Movielens-1M · Movielens-1MRMSE: 0.852 -> 0.881Hurt
Increase λ from 0.5 to 4 (ablation)ChebNet-TV on Movielens-1M · Movielens-1MGender-F1: 0.617 -> 0.505Improved
Increase λ from 0.5 to 4 (ablation)ChebNet-TV on Movielens-1M · Movielens-1MRMSE: 0.881 -> 1.280Hurt
Increase λ (ablation)GAL on Movielens-1M · Movielens-1Mdownstream task performanceHurt
Increase λ (ablation)GAL on Movielens-1M · Movielens-1Madversary performanceImproved
Use the Wasserstein distance rather than Total VariationGAL · Coratraining stabilityImproved
Obfuscate neighborhood-level embeddingsGAL on Movielens-1M · Movielens-1M neighborhood attacksadversary performanceImproved

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