Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Meta-learning from Tasks with Heterogeneous Attribute Spaces
Tomoharu Iwata, Atsutoshi Kumagai
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 one round of attribute/response relation inference (L=0 -> L=1) (ablation) | Ours · OpenML regression (17 target tasks) | MSE: 0.834 -> 0.788 | Improved |
| increase iterations from L=1 to L=2 (ablation) | Ours · OpenML regression (17 target tasks) | MSE: 0.788 -> 0.777 | Improved |
| increase iterations beyond L=2 (ablation) | Ours · OpenML regression (17 target tasks) | MSE: 0.777 -> 0.781 (L=5) | No clear effect |
| sample attributes and responses randomly during training (ablation) | Ours · OpenML regression (17 target tasks) | MSE: 0.848 -> 0.788 | Improved |
| use heterogeneous meta-learning inference network instead of Neural Process | NP · OpenML regression (17 target tasks) | MSE: 0.845 -> 0.788 | Improved |
| replace DS+MAML with Ours | DS+MAML · OpenML regression (17 target tasks) | MSE: 0.854 -> 0.788 | Improved |
| fine-tune on support set | DS · OpenML regression (17 target tasks) | MSE: 0.896 -> 0.887 | No clear effect |
| use proposed classifier prototypes vs DS | DS · OpenML classification | accuracy: 0.621 -> 0.646 | Improved |
| increase number of training tasks | Ours · OpenML regression (17 target tasks) | MSE | Improved |
| increase support set size | Ours · OpenML regression (17 target tasks) | MSE | Improved |
Closest papers by meaning
- Clustered Task-Aware Meta-Learning by Learning From Learning Paths (TPAMI 2023 · similarity 0.89)
- Efficient Heterogeneous Meta-Learning via Channel Shuffling Modulation (ICLR 2024 · similarity 0.88)
- Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models (ICML 2024 · similarity 0.88)
- Subspace Learning for Effective Meta-Learning (ICML 2022 · similarity 0.88)
- Advances and Challenges in Meta-Learning: A Technical Review (TPAMI 2024 · similarity 0.87)
- Learning to Learn with Contrastive Meta-Objective (NeurIPS 2025 · similarity 0.86)
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.
