Probabilistic Multi-Task Feature Selection

By Yu Zhang, Dit-Yan Yeung, Qian Xu. 2010

96 citations recorded by the source corpus.

Subfields: 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 Representation & Self-Supervised Learning

1. Qiang Yang
2. Yu Zhang
3. Yu Zhang
4. Lei Han
5. Yu Zhang
6. Jiayu Zhou
7. Qiang Zhou
8. Qi Zhao

Citations in the corpus

• An Overview of Multi-task Learning (2018, methodology): “Then this prior is extended in [15] to the matrix-variate generalized normal prior to learn relations among tasks and identify outlier tasks simultaneously.”
• A Survey on Multi-Task Learning (2017, methodology): “Moreover, the MTRL model is generalized to the multi-task feature selection problem [41] by learning task relations via the matrix-variate generalized normal distribution.”
• Multi-Stage Multi-Task Feature Learning (2012, neutral): “, 2010; Negahban and Wainwright, 2011) and a common set of shared features (Argyriou et al., 2008; Gong et al., 2012; Kim and Xing, 2009; Kolar et al., 2011; Lounici et al., 2009; Liu et al., 2009; Negahban and Wainwright, 2008; Obozinski et al., 2006; Yang et al., 2009; Zhang et al., 2010).”
• Safe Screening for Multi-Task Feature Learning with Multiple Data Matrices (2015, background): “MTFL has found great success in many real-world applications including but not limited to: breast cancer classification (Zhang et al., 2010), disease progression prediction (Zhou et al., 2012), gene data analysis (Kim and Xing, 2009), and neural semantic basis discovery (Liu et al., 2009a).”
• Learning to Multitask (2018, background): “This approach can be further divided into two categories: shallow approach [9, 2, 43] and deep approach [25].”
• Convex Discriminative Multitask Clustering (2013, background): “The first class shares common feature or kernel representations, such as the hidden units of neural networks [1], [4], [5] and a common representation within the regularization framework [6], [7], [8], [9], [10], [11], [12].”
• Interactive Multi-task Relationship Learning (2016, background): “MTL has many successful applications in board fields such as data mining, computer vision, text mining, bioinformatics and healthcare analytics [22, 33, 16].”
• A Complete Analysis of the l_1, p Group-Lasso (2012, methodology): “We used the same experimental setup as in (Zhang et al., 2010), i.e. we used 70% of each task as training set.”
• Parallel Multi-task Learning (2015, methodology): “By using group-sparsity regularizers based on the l1,p norm where p > 1, the multi-task feature learning (MTFL) method proposed in [7] aims to learn a common subset of features shared by multiple tasks after a linear transformation on the original features and similar to the MTFL method, the objecti”
• Scene Graph Generation from Objects, Phrases and Region Captions (2017, methodology): “Multi-task Learning: Multi-task learning [46, 42, 48, 21, 47] has been used to model the relationships among correlated tasks.”
• Attribute relation learning for zero-shot classification (2014, methodology): “More recently, this approach has been widely applied to many domains demonstrating its effectiveness, such as multi-task learning [44–48], transfer learning [49], multilabel learning [50,51], and multi-view learning [52].”
• Multi-Task Feature Interaction Learning (2016, background): “Such problems are especially prevalent in biological and medical domains, where MTL has achieved significant success, including data analysis on genotype and gene expression [21], breast cancer diagnosis [37] and progression modeling of Alzheimer’s Disease [18], etc.”
• Multi-Task Boosting by Exploiting Task Relationships (2012, methodology): “Moreover, Zhang and Yeung proposed a method in [12] to learn task relationships under the regularization framework for classification and regression problems, and then extended it for feature selection problems in [13].”
• Efficient multi-task feature learning with calibration (2014, background): “It has received a lot of interests and has been successfully applied to a wide range of applications including gene data analysis [18], breast cancer classification [34], neural semantic basis discovery [21] and disease progression prediction [36, 37].”
• On Multiplicative Multitask Feature Learning (2014, methodology): “Later, the (cid:96) 1 ,p norm is generalized to include 1 p ≤ ∞ with a probabilistic interpretation that the resultant MTFL method solves a relaxed optimization problem with a generalized normal prior for all tasks [22].”