AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Learnable Kernel Density Estimation for Graphs and Its Application to Graph-Level Anomaly Detection

Xudong Wang, Ziheng Sun, Chris Ding, Jicong Fan

ICML 2026 · Graph learning › Graph self-supervised learning · approach: Graph anomaly detection

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
add multi-scale KDE instead of the best single bandwidth h=10^-1 (ablation)LGKDE · MUTAGAUROC: 86.92 -> 91.63Improved
use bandwidth 10^-1 rather than 10^2 in single-scale KDE (ablation)LGKDE · MUTAGAUROC: 80.89 -> 86.92Improved
add MMD distance instead of average graph readout (ablation)LGKDE · MUTAGAUROC: 83.89 -> 91.63Improved
add MMD distance instead of sum graph readout (ablation)LGKDE · MUTAGAUROC: 84.73 -> 91.63Improved
add learnable mixture weights instead of fixed weights (ablation)LGKDE · MUTAGAUROC: 88.92 -> 91.63Improved
add learnable mixture weights (ablation)LGKDE · MUTAGFPR95: 36.97 -> 30.80Improved
add multi-scale KDE instead of h=10^-1 (ablation)LGKDE · MUTAGFPR95: 37.95 -> 30.80Improved
jointly train metric and density end-to-end instead of GAE then separate KDELGKDE · MUTAGAUROC: 81.94 -> 91.63Improved
use energy-based spectral perturbation versus random perturbations (ablation)LGKDE · graph anomaly detectionAUROCImproved
use moderate GNN depth of 2-3 layers (ablation)LGKDE · MUTAGAUROCImproved
LGKDE versus best baseline SIGNET on DHFRLGKDE · DHFRAUROC: 72.87 -> 82.58Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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