AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

BAG: Benchmarking Anomaly Detection on Dynamic Graphs

Fengrui Hua, Yiyan Qi, Zikai Wei, Yuxing Tian, Chengjin Xu, Xiaojun Wu, Jia Li, Jian Guo

AAAI 2026 · Graph learning › Graph self-supervised learning · approach: Graph anomaly detection · 2 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
evaluate on organic anomalies instead of synthetic injected anomaliesall benchmarked DyGAD models · edge-level anomaly detectionAUPRC/AUROCHurt
use continuous-time (CTDG) models instead of discrete-time (DTDG) modelsdynamic GNN anomaly detectors · organic edge anomaliesAUPRC/AUROCImproved
use CTDG instead of DTDG models on synthetic anomaliesdynamic GNN anomaly detectors · synthetic edge anomaliesAUPRC/AUROCNo clear effect
use specialized anomaly detection models instead of static GNNs such as SGC and GINsynthetic edge anomaly detection · synthetic edge anomaliesAUPRC/AUROCNo clear effect
decrease the anomaly injection ratio (ablation)static, DTDG and CTDG models · Bitcoin-OTC synthetic anomaliesAUPRC, F1, Rec@KHurt
decrease the anomaly injection ratio (ablation)static, DTDG and CTDG models · Bitcoin-OTC synthetic anomaliesAUROCNo clear effect
use attention-based models instead of non-attention counterpartsGNN anomaly detectors without informative node features · synthetic edge anomaliesAUPRC/AUROCHurt
use too many or too few snapshots for DTDG models (ablation)DTDG models · synthetic edge anomaliesAUPRC/AUROCHurt
use CTDG models instead of DTDG or static methods in terms of costCTDG models · Bitcoin-OTC (5% anomaly ratio)runtime and GPU memoryHurt
use tree-based RFGraph and XGBGraph instead of neural modelsanomaly detection baselines · Bitcoin-OTC (5% anomaly ratio)runtimeImproved

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