Research map / Graph learning / Graph self-supervised learning
From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection
Luzhi Wang, Xuanshuo Fu, He Zhang, Chuang Liu, Xiaobao Wang, Hongbo Liu
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 the energy preference optimization (EPO) loss (ablation) | SIGOOD · BZR/COX2, PTC-MR/MUTAG, Esol/MUV | AUC | Improved |
| use an MLP prompt generator instead of a free parameter matrix (ablation) | SIGOOD · BZR/COX2, PTC-MR/MUTAG, Esol/MUV | AUC | Improved |
| increase prompt generator depth to 3 layers from 1-2 (ablation) | SIGOOD · BZR/COX2, PTC-MR/MUTAG, Esol/MUV | AUC | Improved |
| increase self-improving iterations from 1000 to 10000 (ablation) | SIGOOD · Esol/MUV | AUC: peak 87.72% | Improved |
| set beta to a moderate value (80) (ablation) | SIGOOD · BZR/COX2 | AUC: best 87.36% | Improved |
| SIGOOD vs best test-time baseline GOODAT | test-time graph OOD detection · ClinTox/LIPO | AUC: 62.46 -> 71.33 | Improved |
| SIGOOD vs GOODAT on anomaly detection | graph anomaly detection · DD and p53 | AUC: DD 77.62 -> 72.59; p53 63.27 -> 60.51 | Hurt |
| SIGOOD vs GOODAT on anomaly detection | graph anomaly detection · ENZYMES | AUC: 52.33 -> 76.80 | Improved |
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.
- GOODAT — GOODAT: Towards Test-Time Graph Out-of-Distribution Detection (AAAI 2024) · better on 12 of 14 shared results
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
- GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation (ICLR 2025 · similarity 0.90)
- GOODAT: Towards Test-Time Graph Out-of-Distribution Detection (AAAI 2024 · similarity 0.90)
- Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs (ICML 2024 · similarity 0.89)
- Revisiting Score Propagation in Graph Out-of-Distribution Detection (NeurIPS 2024 · similarity 0.89)
- Redundancy-Aware Test-Time Graph Out-of-Distribution Detection (NeurIPS 2025 · similarity 0.89)
- Bridging OOD Detection and Generalization: A Graph-Theoretic View (NeurIPS 2024 · similarity 0.89)
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.
