AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Disentangled Generation-Based Prototypical Alignment for Few-Shot Unsupervised Domain Adaptation in Graph-Level Anomaly Detection

Zhibin Ni, Chenghao Zhang, Hai Wan, Xibin Zhao

AAAI 2026 · Graph learning › Graph self-supervised learning · approach: Graph anomaly detection · 0 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
add disentangled sample generation (DSG) to baseline (ablation)DGPA backbone · Mutagenicity M2->M0, 10-shotAUROC: 51.65 -> 59.36Improved
add graph-based prototypical self-supervision (GPS) to baseline (ablation)DGPA backbone · Mutagenicity M0->M2, 10-shotAUROC: 50.49 -> 57.16Improved
add GPS to DSG (full DGPA) (ablation)DSG · Mutagenicity M0->M2, 10-shotAUROC: 53.04 -> 63.12Improved
add DSG to GPS (full DGPA) (ablation)GPS · Mutagenicity M2->M0, 5-shotAUROC: 52.21 -> 63.67Improved
use DGPA instead of best baseline on M1->M0, 10-shotPAR · Mutagenicity M1->M0, 10-shotAUROC: 67.72 -> 69.56Improved
use DGPA instead of best baseline on PROTEINS and DDbest baseline · DD->PROTEINS, 10-shotAUROC: 59.37 -> 68.91Improved
set alpha5 (cross-domain loss weight) to 0.7 (ablation)DGPA · all four datasetsAUROCImproved

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