Skip to yearly menu bar Skip to main content


Poster

Transfer Learning with Neural AutoML

Catherine Wong · Neil Houlsby · Yifeng Lu · Andrea Gesmundo

Room 517 AB #158

Keywords: [ Multitask and Transfer Learning ] [ AutoML ]


Abstract:

We reduce the computational cost of Neural AutoML with transfer learning. AutoML relieves human effort by automating the design of ML algorithms. Neural AutoML has become popular for the design of deep learning architectures, however, this method has a high computation cost. To address this we propose Transfer Neural AutoML that uses knowledge from prior tasks to speed up network design. We extend RL-based architecture search methods to support parallel training on multiple tasks and then transfer the search strategy to new tasks. On language and image classification data, Transfer Neural AutoML reduces convergence time over single-task training by over an order of magnitude on many tasks.

Live content is unavailable. Log in and register to view live content