Timezone: »

 
Poster
Learning to Multitask
Yu Zhang · Ying Wei · Qiang Yang

Thu Dec 06 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #113
in Thu Poster Session B »

Multitask learning has shown promising performance in many applications and many multitask models have been proposed. In order to identify an effective multitask model for a given multitask problem, we propose a learning framework called Learning to MultiTask (L2MT). To achieve the goal, L2MT exploits historical multitask experience which is organized as a training set consisting of several tuples, each of which contains a multitask problem with multiple tasks, a multitask model, and the relative test error. Based on such training set, L2MT first uses a proposed layerwise graph neural network to learn task embeddings for all the tasks in a multitask problem and then learns an estimation function to estimate the relative test error based on task embeddings and the representation of the multitask model based on a unified formulation. Given a new multitask problem, the estimation function is used to identify a suitable multitask model. Experiments on benchmark datasets show the effectiveness of the proposed L2MT framework.

Keywords: Multitask and Transfer Learning

Author Information

Yu Zhang (HKUST)
Ying Wei (Tencent AI Lab)
Qiang Yang (Hong Kong University of Science and Technology)

More from the Same Authors