Research map / Label-efficient and robust learning / Knowledge distillation
Nonparametric Teaching for Multiple Learners
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 |
|---|---|---|---|
| Teach multiple target functions simultaneously with vanilla MINT instead of repeating single-learner GFT | GFT teaching of tiger and cheetah figures · Grayscale figures | teaching iterations | Helped |
| Partition one target figure into smaller pieces and teach them concurrently with MINT | Teaching a lion figure · Grayscale figure | teaching efficiency | Helped |
| Add learner communication through a learned linear combination of current functions (ablation) | MINT with RFT or GFT · Three-channel RGB lion | teaching efficiency | Helped |
| Use vanilla MINT without learner communication instead of communicated MINT (ablation) | MINT · Three-channel RGB lion | teaching efficiency | Hurt |
| Use GFT example selection instead of RFT random sampling (ablation) | Multi-learner MINT · Three-channel RGB lion | teaching efficiency | Helped |
| Allow communication to combine initial learner functions that span the target functions (ablation) | Communicated MINT · Synthetic two-learner cosine-function example | teaching iterations | Helped |
Closest papers by meaning
- Nonparametric Iterative Machine Teaching (ICML 2023 · similarity 0.88)
- Iterative Classroom Teaching (AAAI 2019 · similarity 0.88)
- Nonparametric Teaching of Implicit Neural Representations (ICML 2024 · similarity 0.84)
- Cooperative Knowledge Distillation: A Learner Agnostic Approach (AAAI 2024 · similarity 0.84)
- Sharpness-Aware Minimization Activates the Interactive Teaching's Understanding and Optimization (NeurIPS 2024 · similarity 0.84)
- AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals (NeurIPS 2026 · similarity 0.83)
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.