Research map / Learning theory and algorithms / Prediction and decision losses
Iterative Teacher-Aware Learning
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 |
|---|---|---|---|
| model the selected example's teaching context in the learner update | ITAL vs. IMT · synthetic regression, classification, CIFAR-10, Tiny ImageNet, and online IRL | learning performance | Helped |
| use the teacher-aware update instead of the naive update | machine-teacher experiments · regression, classification, and IRL tasks | learning performance | Helped |
| use only one random sample from the mini-batch rather than the full mini-batch (ablation) | Batch learner · machine-teacher experiments | learning performance | No clear effect |
| add teacher-awareness using only 2 data points to approximate the full mini-batch (ablation) | ITAL · machine-teacher experiments | learning performance | Helped |
| use a cooperative teacher rather than random example selection | ITAL · human-teacher study | learning performance | Helped |
| apply the cooperative-teacher model to human teaching rather than machine teaching | ITAL · human-teacher study | learning performance | Hurt |
| use a teacher-aware learner instead of its IMT counterpart | ITAL · human-teacher study | learning effect | Helped |
| model an adversarial teacher and adjust the teacher-awareness term accordingly | ITAL · machine-teacher experiments with adversarial teachers | learning performance | Helped |
Closest papers by meaning
- Iterative Classroom Teaching (AAAI 2019 · similarity 0.88)
- Learning to Teach (ICLR 2018 · similarity 0.88)
- Cooperative Knowledge Distillation: A Learner Agnostic Approach (AAAI 2024 · similarity 0.86)
- Student-Informed Teacher Training (ICLR 2025 · similarity 0.85)
- Toward Student-oriented Teacher Network Training for Knowledge Distillation (ICLR 2024 · similarity 0.85)
- Multi-Teacher Knowledge Distillation with Reinforcement Learning for Visual Recognition (AAAI 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.