Table 10 ID labels used in digraph above, with corresponding paper names, Part I
From: The use of generative adversarial networks to alleviate class imbalance in tabular data: a survey
Paper ID | Paper Name |
|---|---|
1 | Effective data generation for imbalanced learning using conditional generative adversarial networks |
2 | TensorFlow: Largescale machine learning on heterogeneous systems |
3 | Mwmote– majority weighted minority oversampling technique for in balanced data set learning |
4 | A study of the behavior of several methods for balancing machine learning training data |
5 | Safelevelsmote: Safelevelsynthetic minority over sampling technique for handling the class imbalanced problem |
6 | DBSMOTE: Densitybased synthetic minority oversampling technique |
7 | SMOTE: Synthetic minority oversampling technique |
8 | Data mining for imbalanced datasets: An overview |
9 | Smoteboost: Improving prediction of the minority class in boosting |
10 | Start globally optimize locally predict globally: Improving performance on imbalanced data |
11 | Selforganizing map oversampling (SOMO) for imbalanced data set learning |
12 | A review on ensembles for the class imbalance problem: bagging– boosting– and hybrid–based approaches |
13 | Deep sparse rectifier neural networks |
14 | Generative Adversarial Networks |
15 | Learning from imbalanced data sets with boosting and data generation: The DataBoost IM approach |
16 | BorderlineSMOTE: A new oversampling method in imbalanced data sets learning |
17 | Adasyn: Adaptive synthetic sampling approach for imbalanced learning |
18 | Learning from imbalanced data |
19 | Adam: A method for stochastic optimization |
20 | Imbalancedlearn: A python toolbox to tackle the curse of imbalanced datasets in machine learning |
21 | Conditional Generative Adversarial Nets |
22 | Adaptive semiunsupervised weighted oversampling (ASUWO) for imbalanced datasets |
23 | Conditional Image Synthesis with Auxiliary Classifier GANs |
24 | Deep generative image models using a laplacian pyramid of adversarial networks |
25 | AdversarialFeature Learning |
26 | AdversariallyLearned Inference |
27 | Generative adversarial nets |
28 | AutoEncoding VariationalBayes |
29 | Synthesizing the preferred inputs for neurons in neural networks via deep generator networks |
30 | SemiSupervised Learning with Generative Adversarial Networks |
31 | Unsupervised representation learning with deep convolutional generative adversarial networks |
32 | Stochastic Backpropagation and Approximate Inference in DeepGenerative Models |
33 | Improved techniques for training GANs |
34 | Unsupervised and semisupervised learn ing with categorical generative adversarial networks |
35 | Image quality assessment: from error visibility to structural similarity |
36 | Data Augmentation Generative Adversarial Networks |
37 | Wasserstein GAN |
38 | Improved Training of Wasserstein GANs |
39 | Deep Residual Learning for ImageRecognition |
40 | Imagenet classification with deep convolutional neural networks |
41 | BAGAN: Data Augmentation with Balancing GAN |
42 | VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning |
43 | Gradientbased learning applied to document recognition |
44 | Deligan: Generative adversarial networks for diverse and limited data |
45 | Learning multiple layers of features from tiny images |
46 | Generative Adversarial Minority Oversampling |
47 | Deep oversampling framework for classifying imbalanced data |