Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Zero-shot AutoML with Pretrained Models
Ekrem Öztürk, Fabio Ferreira, Hadi Jomaa, Lars Schmidt-Thieme, Josif Grabocka, Frank Hutter
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 |
|---|---|---|---|
| Select a pipeline using geometry-aware ZAP-HPO rather than challenge-winning systems | ZAP pipeline selection · ZAP benchmark | Rank (ALC): 2.07±0.05 vs. 2.53±0.06 (DeepWisdom), 2.64±0.04 (DeepBlueAI), 2.76±0.03 (PASA NJU) | Improved |
| Select a pipeline using geometry-aware ZAP-HPO rather than challenge-winning systems | ZAP pipeline selection · ZAP benchmark | Rank (Normalized AUC): 2.08±0.03 vs. 2.63±0.03 (DeepWisdom), 2.73±0.03 (DeepBlueAI), 2.56±0.03 (PASA NJU) | Improved |
| Use ZAP-HPO instead of challenge-winning systems | Pipeline selection on AutoDL benchmark · AutoDL benchmark | Rank (ALC): 2.16±0.15 vs. 2.46±0.13 (DeepWisdom), 2.76±0.08 (DeepBlueAI), 2.62±0.11 (PASA NJU) | Improved |
| Train ZAP-HPO with only 75% of cost-matrix entries (ablation) | ZAP-HPO · ZAP benchmark | Rank (ALC): 2.09±0.06 | No clear effect |
| Train ZAP-HPO with only 50% of cost-matrix entries (ablation) | ZAP-HPO · ZAP benchmark | Rank (ALC): 2.09±0.05 | No clear effect |
| Train ZAP-HPO with only 25% of cost-matrix entries (ablation) | ZAP-HPO · ZAP benchmark | Rank (ALC): 2.10±0.04 | No clear effect |
| Replace the pairwise ranking objective with least-squares regression (ablation) | ZAP-HPO surrogate · ZAP benchmark | Pipeline identification performance | Hurt |
| Replace the pairwise ranking objective with a triplet margin objective (ablation) | ZAP-HPO surrogate · ZAP benchmark | Pipeline selection performance | Hurt |
| Use ZAP-AS instead of ZAP-HPO for out-of-distribution selection | ZAP pipeline selection · AutoDL benchmark | Rank (ALC): 1.81 (± 0.3) vs. 2.16 (± 0.15) | Mixed |
Closest papers by meaning
- Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning (ICLR 2021 · similarity 0.87)
- How to train your MAML (ICLR 2019 · similarity 0.87)
- Zero-Shot Robustification of Zero-Shot Models (ICLR 2024 · similarity 0.86)
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · similarity 0.86)
- A Generalization Theory for Zero-Shot Prediction (ICML 2025 · similarity 0.85)
- GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder (ICML 2025 · 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.
