Learning Tree Structure in Multi-Task Learning

By Lei Han, Yu Zhang. 2015

77 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics, Evaluation & Benchmarks

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. Xing Xie
4. Ying Wei
5. Hongwei Wang
6. Wenjie Li
7. Miao Zhao
8. Fuzheng Zhang

In Computational Mechanics

1. Qiang Yang
2. Yu Zhang
3. Lei Han
4. Yu Zhang
5. Ying Wei
6. Xing Xie

In Evaluation & Benchmarks

1. Qiang Yang
2. Yu Zhang
3. Lei Han
4. Yu Zhang
5. Xing Xie
6. Ying Wei
7. Fuzheng Zhang
8. Hongwei Wang

Citations in the corpus

• An Overview of Multi-task Learning (2018, background): “Unlike the aforementioned methods where different component matrices have no direct interaction, in [60], with direct connections between component matrices at successive levels, the complex hierarchical/tree structure among tasks can be learned from data.”
• A Survey on Multi-Task Learning (2017, neutral): “Dataset (Reference) Evaluation Metric Feature Learning Low-Rank Task Clustering Task Relation Learning Decomposition [11] [49] [65]/ [66]/ [70]/ [71] [4]/ [88]/ [97] [100]/ [101]/ [102]/ [107]/ [106] School ( [106]) nMSE↓ 0.”
• Learning Sparse Task Relations in Multi-Task Learning (2017, methodology): “…utilizing the Dirichlet process in (Xue et al. 2007), devising some regularizer inspired by the k-means clustering in (Jacob, Bach, and Vert 2008), integer programming in (Kang, Grauman, and Sha 2011), group-sparsity regularizers in (Jawanpuria and Nath 2012; Han and Zhang 2015a) and so on.”
• Learning to Multitask (2018, background): “This approach can be further classified into five categories: low-rank approach [1, 26], task clustering approach [16, 18], task relation learning approach [35, 32, 36, 19, 33], dirty approach [10, 17], and multi-level approach [37, 15].”
• Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation (2019, background): “ified into several categories, including feature learning approach [34, 41], low-rank approach [7, 16], task clustering approach [47], task relation learning approach [12], and decomposition approach [6]. For example, the cross-stitch network [41] determines the inputs of hidden layers in different ”
• Multi-Stage Multi-Task Learning with Reduced Rank (2016, methodology): “Many MTL methods have been proposed by learning common feature representations (Caruana 1997; Argyriou, Evgeniou, and Pontil 2008; Liu, Ji, and Ye 2009; Zhang, Yeung, and Xu 2010), learning task groups (Han and Zhang 2015a), learning task relations (Zhang and Yeung 2010a; Zhang 2013; Zhang and Yeung”