Research map / Learning theory and algorithms / Prediction and decision losses
Teaching Multiple Concepts to a Forgetful Learner
Anette Hunziker, Yuxin Chen, Oisin Mac Aodha, Manuel Gomez Rodriguez, Andreas Krause, Pietro Perona, Yisong Yue, Adish Singla
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 |
|---|---|---|---|
| Use adaptive greedy scheduling instead of LR | Teaching multiple concepts with an HLR learner · German | avg gain: 0.487 -> 0.572 | No clear effect |
| Use adaptive greedy scheduling instead of RR | Teaching multiple concepts · German | avg gain: 0.462 -> 0.572 | Improved |
| Use adaptive greedy scheduling instead of random teaching | Teaching multiple concepts · German | avg gain: 0.467 -> 0.572 | Improved |
| Use adaptive greedy scheduling instead of LR | Teaching multiple concepts with an HLR learner · Biodiversity | avg gain: 0.411 -> 0.475 | Improved |
| Use adaptive greedy scheduling instead of RR | Teaching multiple concepts · Biodiversity | avg gain: 0.390 -> 0.475 | Improved |
| Use adaptive greedy scheduling instead of random teaching | Teaching multiple concepts · Biodiversity | avg gain: 0.251 -> 0.475 | Improved |
| Use adaptive greedy scheduling instead of LR | Teaching common animal species · Biodiversity (common) | avg gain: 0.118 -> 0.143 | No clear effect |
| Use adaptive greedy scheduling instead of RR | Teaching common animal species · Biodiversity (common) | avg gain: 0.150 -> 0.143 | Hurt |
| Use adaptive greedy scheduling instead of random teaching | Teaching common animal species · Biodiversity (common) | avg gain: 0.086 -> 0.143 | Improved |
| Use adaptive greedy scheduling instead of LR | Teaching rare animal species · Biodiversity (rare) | avg gain: 0.668 -> 0.766 | Improved |
| Use adaptive greedy scheduling instead of RR | Teaching rare animal species · Biodiversity (rare) | avg gain: 0.601 -> 0.766 | Improved |
| Use adaptive greedy scheduling instead of random teaching | Teaching rare animal species · Biodiversity (rare) | avg gain: 0.396 -> 0.766 | Improved |
Closest papers by meaning
- Optimal Protocols for Continual Learning via Statistical Physics and Control Theory (ICLR 2025 · similarity 0.85)
- Class Incremental Learning with Multi-Teacher Distillation (CVPR 2024 · similarity 0.84)
- Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective (ICML 2025 · similarity 0.84)
- Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations via Pareto Optimization (ICML 2024 · similarity 0.84)
- Predicting the Susceptibility of Examples to Catastrophic Forgetting (ICML 2025 · similarity 0.84)
- Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning (ICLR 2025 · similarity 0.84)
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.
