Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection
Xueying Ding, Haomin Wen, Simon Klüttermann, Leman Akoglu
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 |
|---|---|---|---|
| train FoMo-0D with mixed priors instead of GMM only (ablation) | FoMo-0D (L4) · ADBench+OddBench+OvRBench (FoMo-0D variants) | average rank: 5.01 -> 5.38 | Hurt |
| add self-evolving curriculum (SEC) to mixed-prior training (ablation) | FoMo-0D (L4, Mix.) · ADBench+OddBench+OvRBench (FoMo-0D variants) | average rank: 5.38 -> 4.78 | Improved |
| add SEC (ablation) | Outformer · ADBench+OddBench+OvRBench (FoMo-0D variants) | average rank: 3.65 -> 3.55 | Improved |
| add SEC (ablation) | Outformer · ADBench+OddBench+OvRBench (FoMo-0D variants) | ELO: 954 -> 1122 | Improved |
| add context ensembling (ablation) | Outformer · ADBench+OddBench+OvRBench (FoMo-0D variants) | average rank: 4.19 -> 3.55 | Improved |
| add mixed priors and SEC (over scaled GMM-only plus ensembling) (ablation) | Outformer · ADBench+OddBench+OvRBench (FoMo-0D variants) | average rank: 4.16 -> 3.55 | Improved |
| add ensembling (ablation) | Outformer · ADBench | average rank: 3.47 -> 2.26 | Improved |
| add GMM prior (ablation) | Outformer (no Ens.) · ADBench | average rank: 4.79 -> 3.47 | Improved |
| add GMM prior (ablation) | Outformer (no Ens.) · SynBench | average AUROC: 0.940 -> 0.971 | Improved |
| add SCM structural outliers (ablation) | Outformer (no Ens.) · ADBench | average rank: 4.04 -> 3.47 | Improved |
| add SCM measurement outliers (ablation) | Outformer (no Ens.) · ADBench | average rank: 4.60 -> 3.47 | Improved |
| add SCM structural outliers (ablation) | Outformer (no Ens.) · SynBench | average AUROC: 0.972 -> 0.971 | No clear effect |
Closest papers by meaning
- ALTBI: Constructing Improved Outlier Detection Models via Optimization of Inlier-Memorization Effect (AAAI 2025 · similarity 0.88)
- DOS: Diverse Outlier Sampling for Out-of-Distribution Detection (ICLR 2024 · similarity 0.87)
- Quantile-Based Maximum Likelihood Training for Outlier Detection (AAAI 2024 · similarity 0.86)
- RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples (ICML 2024 · similarity 0.86)
- Out-of-Distribution Detection with Prototypical Outlier Proxy (AAAI 2025 · similarity 0.86)
- ODIM: Outlier Detection via Likelihood of Under-Fitted Generative Models (ICML 2024 · similarity 0.85)
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.
