Research map / Label-efficient and robust learning / OOD and anomaly detection
Graph Out-of-Distribution Detection via Test-Time Calibration with Dual Dynamic Dictionaries
Yue Hou, Ruomei Liu, Yingke Su, Junran Wu, Ke Xu
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 ID dictionary and OOD dictionary calibration (ablation) | BaCa pretrained baseline · PTC-MR/MUTAG | AUC: 77.59 -> 86.53 | Improved |
| add ID dictionary and OOD dictionary calibration (ablation) | BaCa pretrained baseline · ENZYMES/PROTEIN | AUC: 63.14 -> 67.10 | Improved |
| add the ID dictionary to the OOD dictionary (ablation) | BaCa · PTC-MR/MUTAG | AUC: 85.71 -> 86.53 | Improved |
| add the OOD dictionary to the ID dictionary (ablation) | BaCa · PTC-MR/MUTAG | AUC: 84.65 -> 86.53 | Improved |
| add the OOD dictionary to the ID dictionary (ablation) | BaCa · BZR/COX2 | AUC: 93.66 -> 94.23 | Improved |
| vary graphon mixup lambda range ([0.01,0.2] to [0.8,1.0]) (ablation) | BaCa · AIDS/DHFR, BZR/COX2, PTC-MR/MUTAG, Esol/MUV, ClinTox/LIPO | AUC: e.g. ClinTox/LIPO 79.62 to 80.13 | No clear effect |
| use BaCa test-time calibration instead of GOODAT | GOODAT · 10 ID/OOD pairs (average) | AUC: 76.89 -> 85.26 | Improved |
| use BaCa instead of GOODAT | GOODAT · IMDB-M/IMDB-B | AUC: 79.03 -> 80.93 | Improved |
| vary beta (calibration weight) from 0.1 to 1.0 (ablation) | BaCa · graph OOD datasets | AUC | Mixed |
| vary top-K attention entries from 4 to 64 (ablation) | BaCa · graph OOD datasets | AUC | Mixed |
Closest papers by meaning
- Redundancy-Aware Test-Time Graph Out-of-Distribution Detection (NeurIPS 2025 · similarity 0.91)
- GOODAT: Towards Test-Time Graph Out-of-Distribution Detection (AAAI 2024 · similarity 0.90)
- Graph Out-of-Distribution Detection Goes Neighborhood Shaping (ICML 2024 · similarity 0.90)
- Bridging OOD Detection and Generalization: A Graph-Theoretic View (NeurIPS 2024 · similarity 0.89)
- Revisiting Score Propagation in Graph Out-of-Distribution Detection (NeurIPS 2024 · similarity 0.89)
- GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation (ICLR 2025 · 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.
