Active Multitask Learning Using Both Latent and Supervised Shared Topics

By Ayan Acharya, Raymond J. Mooney, Joydeep Ghosh. 2014

41 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

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. Qiang Yang
2. Yu Zhang
3. Dacheng Tao
4. Meng Fang
5. Mingsheng Long
6. Jianmin Wang
7. Dongrui Wu
8. Sinno Jialin Pan

In Computer Vision and Pattern Recognition

1. Qiang Yang
2. Yu Zhang
3. Dacheng Tao
4. Meng Fang
5. Ling Shao
6. Gabriella Csurka
7. Luc Van Gool
8. Shuicheng Yan

In Representation & Self-Supervised Learning

1. Qiang Yang
2. Yu Zhang
3. Dacheng Tao
4. Meng Fang
5. Mingsheng Long
6. Jianmin Wang
7. Dit-Yan Yeung
8. Yu Zhang

Citations in the corpus

• An Overview of Multi-task Learning (2018, background): “Unlike[66],in[67]wherethelearnerineachtask isasupervisedlatentDirichletallocationmodel,the selection criterion for unlabeled data is the expected error reduction.”
• A Survey on Multi-Task Learning (2017, methodology): “In [121], the expected error reduction is used as a criterion where each task is modeled by a supervised latent Dirichlet allocation model.”
• Active Multi-task Learning via Bandits (2015, methodology): “It is also a variant of [2] and we do not use dimension reduction for the fairness of the comparison;”