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
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 |
|---|---|---|---|
| add disentangled sample generation (DSG) to baseline (ablation) | DGPA backbone · Mutagenicity M2->M0, 10-shot | AUROC: 51.65 -> 59.36 | Improved |
| add graph-based prototypical self-supervision (GPS) to baseline (ablation) | DGPA backbone · Mutagenicity M0->M2, 10-shot | AUROC: 50.49 -> 57.16 | Improved |
| add GPS to DSG (full DGPA) (ablation) | DSG · Mutagenicity M0->M2, 10-shot | AUROC: 53.04 -> 63.12 | Improved |
| add DSG to GPS (full DGPA) (ablation) | GPS · Mutagenicity M2->M0, 5-shot | AUROC: 52.21 -> 63.67 | Improved |
| use DGPA instead of best baseline on M1->M0, 10-shot | PAR · Mutagenicity M1->M0, 10-shot | AUROC: 67.72 -> 69.56 | Improved |
| use DGPA instead of best baseline on PROTEINS and DD | best baseline · DD->PROTEINS, 10-shot | AUROC: 59.37 -> 68.91 | Improved |
| set alpha5 (cross-domain loss weight) to 0.7 (ablation) | DGPA · all four datasets | AUROC | Improved |
Closest papers by meaning
- Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy (NeurIPS 2024 · similarity 0.88)
- DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector (ICLR 2025 · similarity 0.88)
- ARC: A Generalist Graph Anomaly Detector with In-Context Learning (NeurIPS 2024 · similarity 0.88)
- Leveraging Diffusion Model as Pseudo-Anomalous Graph Generator for Graph-Level Anomaly Detection (ICML 2025 · similarity 0.87)
- UniFORM: Towards Unified Framework for Anomaly Detection on Graphs (AAAI 2025 · similarity 0.87)
- UniGAD: Unifying Multi-level Graph Anomaly Detection (NeurIPS 2024 · similarity 0.87)
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.
