Research map / Label-efficient and robust learning / Knowledge distillation
Contact-Distil: Boosting Low Homologous Protein Contact Map Prediction by Self-Supervised Distillation
Qin Wang, Jiayang Chen, Yuzhe Zhou, Yu Li, Liangzhen Zheng, Sheng Wang, Zhen Li, Shuguang Cui
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 self-supervised knowledge distillation from a rich-MSA teacher (ablation) | Contact-Distil · trRosetta validation, MSA count ≤1 | Top L/5: 0.661 -> 0.683 | Improved |
| add self-supervised knowledge distillation from a rich-MSA teacher (ablation) | Contact-Distil · trRosetta validation, MSA count ≤3 | Top L/5: 0.750 -> 0.759 | Improved |
| add ESM-1b pseudo-profile features (ablation) | Contact-Distil · trRosetta validation, MSA count ≤1 | Top L/5: 0.408 -> 0.683 | Improved |
| add ESM-1b pseudo-profile features (ablation) | Contact-Distil · trRosetta validation, MSA count ≤3 | Top L/5: 0.581 -> 0.759 | Improved |
| use Contact-Distil instead of MSA Transformer | low-MSA PCMP · trRosetta validation, MSA count ≤1 | Top L/5: 0.270 -> 0.683 | Improved |
| use Contact-Distil instead of MSA Transformer | low-MSA PCMP · CAMEO-L, MSA count ≤1 | Top L/5: 0.696 -> 0.773 | Improved |
Closest papers by meaning
- MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training (NeurIPS 2024 · similarity 0.84)
- Protein-Nucleic Acid Complex Modeling with Frame Averaging Transformer (NeurIPS 2024 · similarity 0.83)
- MSA Generation with Seqs2Seqs Pretraining: Advancing Protein Structure Predictions (NeurIPS 2024 · similarity 0.83)
- Kernel-Based Evaluation of Conditional Biological Sequence Models (ICML 2024 · similarity 0.82)
- Training Compute-Optimal Protein Language Models (NeurIPS 2024 · similarity 0.82)
- FlexMol: A Flexible Toolkit for Benchmarking Molecular Relational Learning (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.
