Research map / Label-efficient and robust learning / Knowledge distillation
Learning With Single-Teacher Multi-Student
Shan You, Chang Xu, Chao Xu, Dacheng Tao
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 teacher-based difficulty coding (rescaled slacks) (ablation) | gSVM-0 · letter | mean F-measure: 81.75% -> 82.26% | Improved |
| add teacher-based difficulty coding (rescaled slacks) (ablation) | gSVM-0 · satimage | mean accuracy: 94.33% -> 96.28% | Improved |
| add teacher-based difficulty coding (rescaled slacks) (ablation) | gSVM-0 · vowel | mean accuracy: 86.19% -> 90.93% | Improved |
| add teacher-based difficulty coding (rescaled slacks) (ablation) | gSVM-0 · yeast | mean F-measure: 49.71% -> 51.67% | Improved |
| add teacher-based difficulty coding (rescaled slacks) (ablation) | gSVM-0 · shuttle | mean AUC: 94.86% -> 99.28% | Improved |
| gSVM gated binary student vs plain binary SVM | gSVM · letter | mean F-measure: 43.47% -> 82.26% | Improved |
| gSVM student vs SSVM teacher | gSVM · satimage | mean accuracy: 97.05% -> 96.28% | Hurt |
| gSVM student vs SSVM teacher | gSVM · protein | mean accuracy: 80.50% -> 81.01% | Improved |
| use gSVM instead of teacher for binary inference | gSVM · satimage, vowel, letter | relative inference time | Improved |
Closest papers by meaning
- A Unified View on Multi-class Support Vector Classification (JMLR 2016 · similarity 0.86)
- GenSVM: A Generalized Multiclass Support Vector Machine (JMLR 2016 · similarity 0.85)
- Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View (NeurIPS 2020 · similarity 0.85)
- Multi-Class Support Vector Machine with Maximizing Minimum Margin (AAAI 2024 · similarity 0.84)
- Generalized One-Class Learning Using Pairs of Complementary Classifiers (TPAMI 2021 · similarity 0.84)
- Gradient-Based Algorithms for Machine Teaching (CVPR 2021 · 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.
