Research map / Label-efficient and robust learning / Recognition and long-tail
Fine-Grained Machine Teaching with Attention Modeling
Jiacheng Liu, Xiaofeng Hou, Feilong Tang
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 |
|---|---|---|---|
| model learner attention on fine-grained concepts (AMT) instead of JEDI memory-momentum teaching | machine teaching · 100D Gaussian | iterations to reach over 98% accuracy: more than 100 iterations -> no more than 50 iterations | Improved |
| AMT versus JEDI on 2D Gaussian | machine teaching · 2D Gaussian | accuracy | Improved |
| AMT versus SGD, IMT, JEDI on hate speech detection | machine teaching · Hate speech detection | accuracy and objective value | Improved |
| increase learner memory parameters beta and gamma from 0.5 up to 0.9 (ablation) | AMT · Hate speech detection | learning speed | Improved |
| estimate learner predictions with GNN in blackbox setting (not omniscient teacher) | AMT · Hate speech detection (blackbox) | convergence | Mixed |
| GNN estimation instead of label propagation | AMT blackbox · Hate speech detection | estimation speed: 3-10x faster | Improved |
Closest papers by meaning
- Nonparametric Teaching of Attention Learners (ICLR 2026 · similarity 0.87)
- Teaching to Learn: Sequential Teaching of Learners with Internal States (AAAI 2023 · similarity 0.85)
- Scaling Multi-Teacher Distillation for Digital Pathology (NeurIPS 2026 · similarity 0.83)
- EduLLM: Leveraging Large Language Models and Framelet-Based Signed Hypergraph Neural Networks for Student Performance Prediction (ICML 2025 · similarity 0.83)
- Toward Student-oriented Teacher Network Training for Knowledge Distillation (ICLR 2024 · similarity 0.82)
- Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate (NeurIPS 2024 · similarity 0.82)
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.
