AI Paper Atlas

Research map / Graph learning / GNN architectures

Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks

Yan Scholten, Jan Schuchardt, Simon Geisler, Aleksandar Bojchevski, Stephan Günnemann

NeurIPS 2022 · Graph learning › GNN architectures · approach: Graph rewiring and scalable message passing · 4 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
apply GDC graph sparsification at test time (ablation)Message-interception smoothing (GAT) · Cora-ML, second-hop attackscertified ratio: 15,962 -> 14,606Improved
use Monte-Carlo samples more efficiently than prior smoothing certificateMessage-interception smoothing · Cora-ML, pd=0.3, pa=0.85certification time: 25 -> 17Improved
add skip-connection that forwards the non-ablated graph without edges (ablation)Smoothed GNN, node feature ablation · Cora-ML, second-hop attacksrobustness-accuracy tradeoff (AUCRC vs clean accuracy)Improved
ablate 10% less during training than at inference (pt = pe-0.1) (ablation)Smoothed GAT · Cora-ML, second-hop attacksrobustness-accuracy tradeoffImproved
use attention-based architectures (GAT, GATv2) instead of GCN (ablation)Smoothed GNN · Cora-ML, second-hop attacksrobustness-accuracy tradeoffImproved
combine edge deletion and feature ablation instead of either alone (ablation)Smoothed GAT (no skip) · Cora-ML and Citeseerrobustness-accuracy tradeoffImproved
combine edge deletion and feature ablation instead of edge deletion alone (ablation)Smoothed GAT (no skip) · PubMedrobustness-accuracy tradeoffHurt
increase confidence level alpha (ablation)Message-interception smoothing · Cora-MLcertificate strengthNo clear effect
increase number of features d per node for naive baseline (certify rho = rho~/d)Bojchevski et al. (2020) naive baseline · Cora-MLAUCRCHurt

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