Research map / Graph learning / Graph self-supervised learning
Beyond Single Transactions: D-EMAML---Dual-Edge Motif Neural Networks for Enhanced Anti-Money Laundering Detection
Dongmei Han, Min Min, Yuchen Wang, Guoming Xu, Xiaofeng Zhou
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 changed | Where | Measured | Effect |
|---|---|---|---|
| run GINe-style GNN on dual-edge motif graph instead of original graph (GIN) | GIN · DgraphE | AUPRC (%): 48.4 -> 53.8 | Improved |
| run GAT on motif graph instead of original graph | GAT · AMLWorld | AUPRC (%): 8.78 -> 12.9 | Improved |
| run GIN on motif graph instead of original graph | GIN · AMLWorld | AUPRC (%): 7.69 -> 7.58 | No clear effect |
| run GIN on motif graph instead of original graph | GIN · TransBank | AUPRC (%): 4.69 -> 5.84 | Improved |
| add SAIRR redundancy reduction module (ablation) | D-EMGNN · AMLWorld | AUPRC (%): 10.8 -> 15.2 | Improved |
| add type-aware bias term in MGCN (ablation) | D-EMGNN · AMLWorld | AUPRC (%): 7.36 -> 15.2 | Improved |
| add SAIRR and MGCN bias together versus homogeneous variant (ablation) | D-EMGNN · TransBank | AUPRC (%): 7.48 -> 14.2 | Improved |
| keep heterogeneous embeddings (SAIRR) but drop heterogeneous message passing bias (ablation) | D-EMGNN · AMLWorld | AUPRC (%): 8.39 -> 7.36 | Hurt |
| increase motif temporal-span pruning bound eta from 3 to 6 (ablation) | D-EMAML · AMLWorld | AUPRC (%): 2.00 -> 15.2 | Improved |
| increase eta from 5 to 6 (ablation) | D-EMAML · AMLWorld | AUPRC (%): 13.5 -> 15.2 | No clear effect |
| increase eta from 5 to 6 (cost) (ablation) | D-EMAML · AMLWorld | Runtime (min): 65 -> 75 | Hurt |
| use HOGAT or GUIDE higher-order methods adapted to the motif graph | motif graph baselines · TransBank | AUPRC (%): HOGATm 2.62, GUIDEm 3.02 vs GINe 4.69 | Hurt |
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.
- GATe — GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extraction (AAAI 2021) · better on 1 of 1 shared result
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
- UniFORM: Towards Unified Framework for Anomaly Detection on Graphs (AAAI 2025 · similarity 0.86)
- Provably Powerful Graph Neural Networks for Directed Multigraphs (AAAI 2024 · similarity 0.85)
- Graph Anomaly Detection as Dynamical Transport: Training-Free Scoring via Empirical Bayes (NeurIPS 2026 · similarity 0.83)
- Context-aware Graph Neural Network for Graph-based Fraud Detection with Extremely Limited Labels (AAAI 2025 · similarity 0.83)
- Unveiling the Threat of Fraud Gangs to Graph Neural Networks: Multi-Target Graph Injection Attacks Against GNN-Based Fraud Detectors (AAAI 2025 · similarity 0.83)
- Revisiting Graph-Based Fraud Detection in Sight of Heterophily and Spectrum (AAAI 2024 · similarity 0.83)
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.
