Parallel Multi-task Learning

By Yu Zhang. 2015

24 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics, 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. Sinno Jialin Pan
4. Mingsheng Long
5. Jianmin Wang
6. Sulin Liu
7. Qirong Ho
8. Dongrui Wu

In Computational Mechanics

1. Qiang Yang
2. Yu Zhang
3. Qirong Ho
4. Sinno Jialin Pan
5. Sulin Liu
6. Virginia Smith
7. Ameet Talwalkar

In Computer Vision and Pattern Recognition

1. Qiang Yang
2. Yu Zhang
3. Sinno Jialin Pan
4. Qirong Ho
5. Sulin Liu
6. Gabriella Csurka
7. Dacheng Tao
8. Michael R. Lyu

In Representation & Self-Supervised Learning

1. Qiang Yang
2. Yu Zhang
3. Sinno Jialin Pan
4. Mingsheng Long
5. Jianmin Wang
6. Sulin Liu
7. Qirong Ho
8. Dongrui Wu

Citations in the corpus

• An Overview of Multi-task Learning (2018, methodology): “In [82], a parallelMTLmethod is devised to solve a subproblemof theMTRLmodel [44], which also occurs in many regularized methodsbelonging to the task-relation learning approach.”
• A Survey on Multi-Task Learning (2017, methodology): “(20) implies that WTW follows a Wishart distribution asW(·|0,Ω), Zhang and Yeung [91] generalize it as (WTW)t ∼ W(·|0,Ω), (22) where t is a positive integer to model high-order task relationships.”
• Distributed Multi-Task Relationship Learning (2017, methodology): “In addition, our algorithm can solve the same type of problem as PMTL under the distributed machine learning setting, while PMTL cannot be applied directly when data of different tasks are stored on different local machines.”