Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources.
Yun-Yun TsaiPin-Yu ChenTsung-Yi HoPublished in: ICML (2020)
Keyphrases
- black box
- limited resources
- transfer learning
- data sets
- data analysis
- labeled data
- black boxes
- data mining techniques
- data sources
- training data
- neural network
- predictive model
- knowledge transfer
- learning tasks
- machine learning models
- similarity measure
- cross domain
- historical data
- reinforcement learning
- test set
- active learning
- text classification
- knowledge discovery
- data points