Learning to Multitask
This work addresses the model selection challenge in multitask learning for researchers and practitioners, but it is incremental as it builds on existing multitask models and datasets.
The paper tackles the problem of selecting an effective multitask learning model for a given multitask problem by proposing a learning framework called L2MT, which uses historical experience and a graph neural network to estimate model performance, with experiments on benchmark datasets showing its effectiveness.
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 consists 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.