K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning.
Pramod Kaushik MudrakartaMark SandlerAndrey ZhmoginovAndrew G. HowardPublished in: ICLR (Poster) (2019)
Keyphrases
- multi task
- transfer learning
- multi task learning
- learning tasks
- knowledge transfer
- multitask learning
- reinforcement learning
- multiple tasks
- gaussian processes
- transfer knowledge
- labeled data
- cross domain
- collaborative filtering
- text categorization
- active learning
- learning algorithm
- structure learning
- machine learning algorithms
- semi supervised learning
- learning problems
- feature selection
- machine learning
- information gain
- text classification