Feature Partitioning for Efficient Multi-Task Architectures

Wang Chong
Wang Chong
Li Li-Jia
Li Li-Jia
Cited by: 1|Bibtex|Views34
Other Links: arxiv.org

Abstract:

Multi-task learning holds the promise of less data, parameters, and time than training of separate models. We propose a method to automatically search over multi-task architectures while taking resource constraints into consideration. We propose a search space that compactly represents different parameter sharing strategies. This provid...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments