On Multiplicative Multitask Feature Learning
By Xin Wang, Jinbo Bi, Shipeng Yu, Jiangwen Sun. 2014
52 citations recorded by the source corpus.
We investigate a general framework of multiplicative multitask feature learning which decomposes each task's model parameters into a multiplication of two components. One of the components is used across all tasks and the other component is task-specific. Several previous methods have been proposed as special cases of our framework. We study the theoretical properties of this framework when different regularization conditions are applied to the two decomposed components. We prove that this framework is mathematically equivalent to the widely used multitask feature learning methods that are based on a joint regularization of all model parameters, but with a more general form of regularizers. Further, an analytical formula is derived for the across-task component as related to the task-specific component for all these regularizers, leading to a better understanding of the shrinkage effect. Study of this framework motivates new multitask learning algorithms. We propose two new learning formulations by varying the parameters in the proposed framework. Empirical studies have revealed the relative advantages of the two new formulations by comparing with the state of the art, which provides instructive insights into the feature learning problem with multiple tasks.
Subfields: Artificial Intelligence, Computational Mechanics, Optimization & Training
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
- Qiang Yang
- Yu Zhang
- Mingsheng Long
- Jianmin Wang
- Dongrui Wu
- Sinno Jialin Pan
- Sebastian Ruder
- Philip S. Yu
In Computational Mechanics
In Optimization & Training
Citations in the corpus
- An Overview of Multi-task Learning (2018, background): “This model is extended in [13,14] to more general settings.”
- A Survey on Multi-Task Learning (2017, background): “[36] propose a multi-component product based decomposition for wij where the number of components in the decomposition can be arbitrary instead of only 2 in [34], [35].”