Adversarial Dropout for Supervised and Semi-Supervised Learning
Authors: Sungrae Park, JunKeon Park, Su-Jin Shin, Il-Chul Moon
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | This section evaluates the empirical performance of adversarial dropout for supervised and semi-supervised classification tasks on three benchmark datasets, MNIST, SVHN, and CIFAR-10. |
| Researcher Affiliation | Academia | Sungrae Park, Jun Keon Park, Su-Jin Shin, Il-Chul Moon Department of Industrial and System Engineering KAIST Deajeon, South Korea {sungraepark, alex3012, sujin.shin, icmoon}@kaist.ac.kr |
| Pseudocode | Yes | Algorithm 1: Finding Adversarial Dropout Condition |
| Open Source Code | No | The paper does not provide any concrete access to source code for the methodology described in this paper, nor does it include specific repository links or explicit code release statements. |
| Open Datasets | Yes | This section evaluates the empirical performance of adversarial dropout for supervised and semi-supervised classification tasks on three benchmark datasets, MNIST, SVHN, and CIFAR-10. [...] We benchmark our method on the MNIST dataset (Le Cun et al. 1998) [...] We experimented the performances of the supervised and the semi-supervised tasks on the SVHN (Netzer et al. 2011) and the CIFAR-10 (Krizhevsky and Hinton 2009) datasets. |
| Dataset Splits | Yes | The supervised learning used 60,000 instances for training with full labels. The semi-supervised learning used 1,000 randomly selected instances with their labels and 59,000 instances with only their input images. [...] In SVHN, 1,000 labeled and 72,257 unlabeled data were used for training. In CIFAR-10, 4,000 labeled and 46,000 unlabeled data were used. |
| Hardware Specification | No | The paper does not provide any specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. It lacks mentions of specific hardware components like NVIDIA A100, Intel Xeon, or cloud instance types. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers like Python 3.8, PyTorch 1.9) needed to replicate the experiment. |
| Experiment Setup | Yes | Our basic structure is a convolutional neural network (CNN) containing three convolutional layers, which filters are 32, 64, and 128, respectively, and three max-pooling layers sized by 2x2. The adversarial dropout applied only on the final hidden layer. The structure detail and the hyperparameters are described in Appendix B.1. [...] When we trained the autoencoder, we set the dropout with p = 0.5, and we calculated the reconstruction error between the input data and the output layer as a loss function to update the weight values of the autoencoder with the standard dropout. On the other hand, the adversarial dropout error is also considered when we update the weight values of the autoencoder with the parameters, λ = 0.2, and δ = 0.3. |