Learning to Multitask

By Yu Zhang, Ying Wei, Qiang Yang. 2018

54 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Han-Jia Ye
2. De-chuan Zhan
3. Wei-Lun Chao
4. Qiang Yang
5. Yu Zhang
6. Yaochu Jin
7. Sam Kwong
8. Mingsheng Long

Citations in the corpus

• A Survey on Multi-Task Learning (2017, methodology): “For example, a learning to multi-task framework is proposed in [110] to learn a suitable multi-task model for a given multi-task problem under problem (34) by utilizing Σ to characterize the corresponding multi-task model.”
• How to Train Your MAML to Excel in Few-Shot Classification (2021, background): “Recent years have witnessed an abundance of new approaches on meta-learning [29, 30, 48, 61, 63, 64, 68, 77, 79, 80, 94, 98], developed in various areas including few-shot learning [70, 85, 89, 105, 107, 110, 111, 115], optimization [3, 9, 53, 108], reinforcement and imitation learning [23, 24, 31, ”
• Revisiting Meta-Learning as Supervised Learning (2020, background): “…(Riemer et al., 2019; Kaiser et al., 2017; Al-Shedivat et al., 2018; Clavera et al., 2019), transfer and multitask learning (Ying et al., 2018; Zhang et al., 2018b), active learning (Ravi and Larochelle, 2018; Sharma et al., 2018; Bachman et al., 2017; Ravi and Larochelle, 2018; Sharma et…”
• Pareto Multi-Task Learning (2019, background): “Recently, some learning-based methods have been proposed to solve MTL problems [36, 44].”
• Few-shot learning with adaptively initialized task optimizer: a practical meta-learning approach (2019, background): “2018), domain adaptation (Motiian et al. 2017; Zhang et al. 2018), intimation learning (Yu et al.”