Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Functional Ensemble Distillation
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 |
|---|---|---|---|
| Add mixup augmentation to FED (ablation) | FED · STL-10 | accuracy (%): 65.06 -> 80.94 | Helped |
| Add mixup augmentation to FED (ablation) | FED · CIFAR-10 | accuracy (%): 92.58 -> 93.68 | Helped |
| Add mixup augmentation to FED (ablation) | FED · CIFAR-100 | accuracy (%): 68.34 -> 74.56 | Helped |
| Add mixup augmentation to EnDD (ablation) | EnDD · STL-10 | accuracy (%): 72.23 -> 78.40 | Helped |
| Add mixup augmentation to EnDD (ablation) | EnDD · CIFAR-10 | accuracy (%): 90.35 -> 90.83 | Helped |
| Add mixup augmentation to EnDD (ablation) | EnDD · CIFAR-100 | accuracy (%): 71.16 -> 68.78 | Hurt |
| Distill the ensemble with FED rather than EnDD + mixup (ablation) | EnDD + mixup · STL-10 | accuracy (%): 78.40 -> 80.94 | Helped |
| Distill the ensemble with FED rather than EnDD + mixup (ablation) | EnDD + mixup · CIFAR-10 | accuracy (%): 90.83 -> 93.68 | Helped |
| Distill the ensemble with FED rather than EnDD + mixup (ablation) | EnDD + mixup · CIFAR-100 | accuracy (%): 68.78 -> 74.56 | Helped |
Closest papers by meaning
- Bayesian Knowledge Distillation: A Bayesian Perspective of Distillation with Uncertainty Quantification (ICML 2024 · similarity 0.87)
- Ensemble Distribution Distillation via Flow Matching (ICML 2025 · similarity 0.85)
- Group Distributionally Robust Dataset Distillation with Risk Minimization (ICLR 2025 · similarity 0.84)
- Knowledge Distillation of Uncertainty using Deep Latent Factor Model (NeurIPS 2025 · similarity 0.84)
- The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model (NeurIPS 2025 · similarity 0.84)
- Simultaneous identification of models and parameters of scientific simulators (ICML 2024 · 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.