Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
The Advantage of Conditional Meta-Learning for Biased Regularization and Fine Tuning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Condition the meta-parameter on side information instead of using one shared parameter | Fine-tuning on synthetic two-cluster tasks with different cluster targets · Synthetic clusters | absolute error | Helped |
| Condition the meta-parameter on side information instead of using one shared parameter | Fine-tuning on synthetic two-cluster tasks with opposing targets and mean target zero · Synthetic clusters | absolute error | Helped |
| Condition the meta-parameter on side information | Fine-tuning on a homogeneous, one-cluster task environment · Synthetic clusters | absolute error | No clear effect |
| Use a conditional meta-parameter rather than an unconditional mean parameter | Fine-tuning on tasks whose targets lie on a circle and whose side information is the circle parameter · Synthetic circle | absolute error | Helped |
| Use Fourier random features instead of the true circle feature map (ablation) | Conditional fine-tuning on the synthetic circle · Synthetic circle | absolute error | Mixed |
Closest papers by meaning
- Conditional Meta-Learning of Linear Representations (NeurIPS 2022 · similarity 0.91)
- Structured Prediction for Conditional Meta-Learning (NeurIPS 2020 · similarity 0.90)
- Meta-Learning Requires Meta-Augmentation (NeurIPS 2020 · similarity 0.90)
- Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models (ICML 2024 · similarity 0.89)
- Learning to Learn with Contrastive Meta-Objective (NeurIPS 2025 · similarity 0.87)
- Memory-Reduced Meta-Learning with Guaranteed Convergence (AAAI 2025 · 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.