dsMTL: a computational framework for privacy-preserving, distributed multi-task machine learning.
Han CaoYoucheng ZhangJan BaumbachPaul R. BurtonDominic B. DwyerNikolaos KoutsoulerisJulian O. MatschinskeYannick MarconSivanesan RajanThilo RiegPatricia Ryser-WelchJulian SpäthCarl HerrmannEmanuel SchwarzPublished in: Bioinform. (2022)
Keyphrases
- privacy preserving
- computational framework
- multi task
- learning tasks
- machine learning
- horizontally partitioned data
- horizontally partitioned
- multi task learning
- multi party
- partitioned data
- learning problems
- privacy sensitive
- privacy preserving data mining
- transfer learning
- privacy preservation
- feature selection
- secure multiparty computation
- computational model
- privacy preserving classification
- vertically partitioned data
- machine learning algorithms
- multi class
- learning algorithm
- sensitive information
- supervised learning
- privacy protection
- data privacy
- data mining
- privacy concerns
- private information
- learning experience
- text classification
- differential privacy
- preserving privacy
- active learning
- distributed data
- information gain
- decision trees
- semi supervised learning
- multiple kernel learning
- kernel methods
- scalar product
- reinforcement learning
- text mining