Research map / Graph learning / GNN architectures
Guided Dropout
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 |
|---|---|---|---|
| Use Guided Dropout (DR) instead of conventional dropout | NN[8192,3] · CIFAR10 | test accuracy (%): 59.86 -> 61.32 | Helped |
| Use Guided Dropout (DR) instead of conventional dropout | NN[8192,3] · CIFAR100 | test accuracy (%): 31.63 -> 33.15 | Helped |
| Use Guided Dropout (DR) instead of conventional dropout | NN[8192,3] · SVHN | test accuracy (%): 86.79 -> 87.99 | Helped |
| Use Guided Dropout (DR) instead of conventional dropout | NN[8192,3] · Tiny ImageNet | test accuracy (%): 14.44 -> 17.74 | Helped |
| Use Guided Dropout (DR) instead of conventional dropout | NN[8192,3] · MNIST | test accuracy (%): 98.53 -> 98.89 | Helped |
| Use Guided Dropout (DR) instead of conventional dropout | ResNet18 · CIFAR10 | test accuracy (%): 94.09 -> 94.12 | No clear effect |
| Use Guided Dropout (DR) instead of conventional dropout | ResNet18 · CIFAR100 | test accuracy (%): 75.44 -> 77.52 | Helped |
| Use Guided Dropout (DR) instead of conventional dropout | ResNet18 · SVHN | test accuracy (%): 96.66 -> 97.18 | Helped |
| Use Guided Dropout (DR) instead of conventional dropout | ResNet18 · Tiny ImageNet | test accuracy (%): 64.13 -> 64.33 | No clear effect |
| Use Guided Dropout (DR) instead of conventional dropout | Wide-ResNet 28-10 · CIFAR10 | test accuracy (%): 96.27 -> 96.89 | Helped |
| Use Guided Dropout (DR) instead of conventional dropout | Wide-ResNet 28-10 · CIFAR100 | test accuracy (%): 82.49 -> 82.84 | Helped |
| Use Guided Dropout (DR) instead of conventional dropout | Wide-ResNet 28-10 · SVHN | test accuracy (%): 96.75 -> 97.23 | Helped |
Closest papers by meaning
- Demystifying Dropout (ICML 2019 · similarity 0.92)
- Dropout with Expectation-linear Regularization (ICLR 2017 · similarity 0.90)
- Jumpout : Improved Dropout for Deep Neural Networks with ReLUs (ICML 2019 · similarity 0.90)
- Dropout Reduces Underfitting (ICML 2023 · similarity 0.89)
- On the Implicit Bias of Dropout (ICML 2018 · similarity 0.89)
- Stochastic Modified Equations and Dynamics of Dropout Algorithm (ICLR 2024 · similarity 0.87)
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.