Fairness and Robustness in Invariant Learning: A Case Study in Toxicity Classification.
Robert AdragnaElliot CreagerDavid MadrasRichard S. ZemelPublished in: CoRR (2020)
Keyphrases
- learning process
- pattern recognition
- incremental learning
- feature selection
- supervised learning
- learning algorithm
- discriminative learning
- automatic classification
- classification accuracy
- structured output
- neural network
- mobile learning
- online learning
- training set
- reinforcement learning
- feature set
- image classification
- support vector machine
- unsupervised learning
- benchmark datasets
- active learning
- classification algorithm
- learning tasks
- prior knowledge
- inductive inference
- prostate cancer
- kernel machines
- feature extraction