paper-with-me

홈 › Papers

On Multiplicative Multitask Feature Learning

2016-10-24 · NeurIPS 2014 12 · Xin Wang, Jinbo Bi, Shipeng Yu, Jiangwen Sun

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.

📄 PDF Abstract BibTeX arXiv:1610.07563

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning

2023-03-06 · Zhen Wang, Rameswar Panda, Leonid Karlinsky, Rogerio Feris 외

Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstrea…

Transfer Learning

Removing the Feature Correlation Effect of Multiplicative Noise

2018-09-19 · NeurIPS 2018 12 · Zijun Zhang, Yining Zhang, Zongpeng Li

Multiplicative noise, including dropout, is widely used to regularize deep neural networks (DNNs), and is shown to be effective in a wide range of architectures and tasks. From an information perspective, we consider inj…

Feature Correlationimage-classificationImage Classification

Visual representations derived from multiplicative interactions

2020-10-09 · NeurIPS Workshop SVRHM 2020 12 · Eric Elmoznino, Michael Bonner

Biological sensory systems appear to rely on canonical nonlinear computations that can be readily adapted to a broad range of representational objectives. Here we test the hypothesis that one such computation—multiplicat…

Saliency-Regularized Deep Multi-Task Learning

2022-07-03 · Guangji Bai, Liang Zhao

Multitask learning is a framework that enforces multiple learning tasks to share knowledge to improve their generalization abilities. While shallow multitask learning can learn task relations, it can only handle predefin…

image-classificationImage ClassificationMulti-Task LearningRelation

The Benefit of Multitask Representation Learning

2015-05-23 · Andreas Maurer, Massimiliano Pontil, Bernardino Romera-Paredes

We discuss a general method to learn data representations from multiple tasks. We provide a justification for this method in both settings of multitask learning and learning-to-learn. The method is illustrated in detail …

Representation Learning