AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Learning Discriminative and Generalizable Anomaly Detector for Dynamic Graph with Limited Supervision

Yuxing Tian, Yiyan Qi, Fengran Mo, Weixu Zhang, Jian Guo, Jian-Yun Nie

ICML 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 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 residual representation encoding (ablation)SDGAD on TCL · WikipediaF1: 5.29 ± 5.69 -> 8.34 ± 2.72Improved
add residual representation encoding (ablation)SDGAD on TCL · MOOCAUROC: 69.14 ± 2.48 -> 72.87 ± 1.40Improved
add representation restriction loss L_RR (ablation)SDGAD on TCL · WikipediaF1: 6.01 ± 0.72 -> 8.34 ± 2.72Improved
add representation restriction loss L_RR (ablation)SDGAD on TCL · WikipediaAUROC: 79.44 ± 0.80 -> 80.36 ± 0.69No clear effect
use bi-boundary optimization instead of single boundary (ablation)SDGAD on TCL · WikipediaF1: 7.41 ± 3.29 -> 8.34 ± 2.72Improved
use bi-boundary optimization instead of single boundary (ablation)SDGAD on TCL · MOOCF1: 6.42 ± 0.97 -> 7.15 ± 0.64Improved
apply SDGAD framework to TCL encoderTCL · WikipediaF1: 2.41 ± 0.0 -> 8.34 ± 2.72Improved
apply SDGAD framework to DyGFormer encoderDyGFormer · WikipediaAUROC: 85.58 -> 86.60Improved
apply SDGAD to DyGFormerDyGFormer · WikipediaAP: 2.58 -> 3.71Hurt
set decision margin tau to 0.1 instead of 0.05 (ablation)SDGAD on TCL · WikipediaF1: 5.06 -> 8.34Improved
set decision margin tau to 0.1 instead of 0.2 (ablation)SDGAD on TCL · WikipediaAUROC: 77.26 -> 80.36Improved
lower gamma from 0.99 to 0.95 (ablation)SDGAD on TCL · WikipediaF1: 8.34 -> 3.51Hurt

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