RULER: discriminative and iterative adversarial training for deep neural network fairness.
Guanhong TaoWeisong SunTingxu HanChunrong FangXiangyu ZhangPublished in: ESEC/SIGSOFT FSE (2022)
Keyphrases
- neural network
- training process
- training algorithm
- feed forward neural networks
- feedforward neural networks
- discriminative training
- neural network training
- multi layer perceptron
- backpropagation algorithm
- back propagation
- training patterns
- artificial neural networks
- pattern recognition
- neural network model
- training set
- semi supervised
- training examples
- resource allocation
- training phase
- feature extraction
- neural network structure
- multi layer
- deep architectures
- unsupervised learning
- error back propagation
- training data
- neural network is trained
- discriminatively trained
- positive training examples
- adaptive learning rate
- train a neural network
- neural nets
- bp neural network
- feed forward
- supervised learning
- object detection
- support vector
- multi agent
- feature selection