AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection

Xuanwen Huang, Yang Yang, Yang Wang, Chunping Wang, Zhisheng Zhang, Jiarong Xu, Lei Chen, Michalis Vazirgiannis

NeurIPS 2022 · Graph learning › Graph self-supervised learning · approach: Graph anomaly detection · 28 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
use graph structure with node features (GCN) instead of MLPMLPs · DGraph testAUC: 0.723 -> 0.751Improved
use dynamic (temporal) information via TGAT instead of GCNGCN · DGraph testAUC: 0.751 -> 0.792Improved
use specialized GAD methods instead of general GNNsGCN/SAGE · DGraph testAUC: 0.778 -> 0.752Hurt
add background-node indicator feature (ablation)GCN · DGraph testAUC: 0.751 -> 0.768Improved
add background-node indicator feature (ablation)GCN · DGraph testAP: 0.037 -> 0.037No clear effect
treat background nodes as separate node type with RGCN (ablation)GCN · DGraph testAUC: 0.751 -> 0.784Improved
remove increasing proportion of background nodes (ablation)GCN · DGraph testAUC: 0.76 -> 0.72Hurt
add missing-value flags and imputation tricks (ablation)GCN · DGraph testAUC: +0.39% AUCImproved
add missing-value flags and imputation tricks (ablation)MLP · DGraph testAUC: +0.11% AUCImproved

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