Back to Search
Start Over
Feature Partitioning for Efficient Multi-Task Architectures
- Publication Year :
- 2019
-
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 provides more effective coverage and sampling of the space of multi-task architectures. We also present a method for quick evaluation of different architectures by using feature distillation. Together these contributions allow us to quickly optimize for efficient multi-task models. We benchmark on Visual Decathlon, demonstrating that we can automatically search for and identify multi-task architectures that effectively make trade-offs between task resource requirements while achieving a high level of final performance.
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.1908.04339
- Document Type :
- Working Paper