Discriminative Sample Generation for Deep Imbalanced Learning
Authors: Ting Guo, Xingquan Zhu, Yang Wang, Fang Chen
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments and comparisons confirm that DVAAN significantly alleviates the class imbalance and delivers accurate models for deep learning from imbalanced data. |
| Researcher Affiliation | Academia | 1Faculty of Eng. & Info. Tech., University of Technology Sydney, Australia 2Dept. of Computer & Electrical Eng. and Computer Science, Florida Atlantic University, USA Ting.Guo@uts.edu.au, xzhu3@fau.edu, {Yang.Wang, Fang.Chen}@uts.edu.au |
| Pseudocode | Yes | Algorithm 1 Training the DVAAN model |
| Open Source Code | No | The paper does not provide a link to open-source code for the described methodology or explicitly state that the code is publicly available. |
| Open Datasets | Yes | MNIST. is a handwritten digit database commonly used for deep learning. It has a training set of 60,000 examples, and a test set of 10,000 samples1. Fashion-MNIST. is a dataset of Zalando s article images consisting of a training set of 60,000 examples and a test set of 10,000 samples. Each example is a 28x28 grayscale image, associated with a label from 10 classes2. CIFAR-10. is one of the most widely used datasets for deep learning. It contains 60,000 32x32 color images in 10 different classes...3. TIS. is used to predict the Translation Initiation Sites (TIS) at which the translation from a messenger RNA to a protein sequence was initiated. The dataset has two classes and 927 features4. |
| Dataset Splits | No | The paper mentions training and testing sets for datasets but does not explicitly specify a validation set or its split details for general reproduction. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for running the experiments (e.g., GPU models, CPU types). |
| Software Dependencies | No | The paper mentions that the model is "implemented using Tensorflow toolbox" but does not specify any version numbers for TensorFlow or other software dependencies. |
| Experiment Setup | No | The paper describes the network architecture and some specific parameters for model variants (e.g., "fix µ = 3"), but it lacks comprehensive details on hyperparameters such as learning rates, batch sizes, optimizers, and the number of training epochs for the main DVAAN model. |