Learning Multiple Related Tasks using Latent Independent Component Analysis

By Jian Zhang, Zoubin Ghahramani, Yiming Yang. 2005

129 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A Survey on Multi-Task Learning (2017, background): “Moreover, in [47], [48], a latent variable model is proposed for”
Multi-Stage Multi-Task Feature Learning (2012, neutral): “…that all tasks should share some common structures including the prior or parameters of Bayesian models (Schwaighofer et al., 2005; Yu et al., 2005; Zhang et al., 2006), a similarity metric matrix (Parameswaran and Weinberger, 2010), a classification weight vector (Evgeniou and Pontil, 2004), a…”
Bregman Divergence-Based Regularization for Transfer Subspace Learning (2010, methodology): “…correction models have been developed to reduce the sample selection bias problem [24], [25], [17]; and the latent independent component analysis [10] has been proposed for text classification and the scheme utilizes Laplace distributions to model hidden sources to identify independent…”
Safe Screening for Multi-Task Feature Learning with Multiple Data Matrices (2015, background): “…have shown that learning multiple related tasks (MTL) simultaneously often provides superior predictive performance relative to learning each tasks independently (Ando and Zhang, 2005, Argyriou et al., 2008, Bakker and Heskes, 2003, Evgeniou et al., 2005, Zhang et al., 2006, Chen et al., 2013).”
Learning a Kernel for Multi-Task Clustering (2011, methodology): “…shared subspace (Ando and Zhang 2005) (Argyriou, Evgeniou, and Pontil 2006), using the common prior of model parameters (Evgeniou and Pontil 2004) (Zhang, Ghahramani, and Yang 2005) (Zhang and yan Yeung 2010) and kernel methods (Micchelli and Pontil 2004) (Pan, Kwok, and Yang 2008) (Duan et al.…”
Learning Multiple Tasks with a Sparse Matrix-Normal Penalty (2010, background): “Along this direction, researchers proposed to infer task structure via principal components [1, 12], independent components [30] and covariance [2, 3] in the parameter space, to select a common subset of features [9, 23], as well as to use shared hidden nodes in neural networks [6, 11].”
A convex formulation for learning shared structures from multiple tasks (2009, methodology): “Introduction The problem of multi-task learning (Caruana, 1997) has recently received broad attention in areas such as machine learning, data mining, computer vision, and bioinformatics (Heisele et al., 2001; Ando & Zhang, 2005; Ando, 2007; Xue et al., 2007; Yu et al., 2007; Argyriou et al.,…”
Large-Scale Personalized Human Activity Recognition Using Online Multitask Learning (2013, background): “Ravi et al. [3] used decision trees (DTs), support vector machines (SVMs) and K-nearest neighbors (KNNs) models for classification.”
Multi-Task Learning with Gaussian Matrix Generalized Inverse Gaussian Model (2013, background): “…tasks (Xue et al., 2007; Yu et al., 2007; Jacob et al., 2008) or by mining the common feature structures shared by the tasks (Ando & Zhang, 2005; Zhang et al., 2005; Argyriou et al., 2006; Obozinski et al., 2009; Chen et al., 2009; Rai & Daumé III, 2010), which is equivalent to estimating a…”
Multi-Task Learning for Classification with Dirichlet Process Priors (2007, methodology): “…decade (Bakker and Heskes, 2003; Baxter, 1995, 2000; Caruana, 1997; Lawrence and Platt, 2004; Thrun and O’Sullivan, 1996; Yu et al., 2003; Zhang et al., 2006) and has been applied successfully to computer vision (Fei-Fei et al., 2004; Thrun and O’Sullivan, 1996) and information retrieval (Yu et…”
Robust multi-task learning with t-processes (2007, background): “References Ando, R. K., & Zhang, T. (2005).”
Flexible latent variable models for multi-task learning (2008, background): “Our framework is a special case of Hierarchical Bayesian model which generalizes and extends our previous work [23].”
A Spectral Regularization Framework for Multi-Task Structure Learning (2007, background): “Recently, there has been renewed interest in the problem of multi-task learning, see [2, 4, 5, 14, 16, 19] and references therein.”
Flexible Modeling of Latent Task Structures in Multitask Learning (2012, methodology): “In particular, RANK performs worse than our method, potentially because all weight vectors share the same subspace which may not be desirable if not all the tasks are related with each other.”
Robust multi-task feature learning (2012, unknown): “Under explicit parameter sharing, all the tasks explicitly share some common parameters; examples include hidden units in neural networks [8, 5], prior in hierarchical Bayesian models [4, 31, 36, 38], parameters of Gaussian process [18], feature mapping matrix [1], classification weight [11] and sim”
Convex multi-task feature learning (2008, methodology): “, using principal component analysis (PCA) or independent component analysis (ICA)), there has been only limited work (Ando and Zhang 2005; Baxter 2000; Jebara 2004; Zhang et al. 2006) in the multi-task supervised learning setting.”
Multi-Stage Multi-Task Learning with Reduced Rank (2016, background): “…all the learning tasks share some common structure including, for example, hidden units in neural networks, probabilistic priors in Bayesian model (Zhang, Ghahramani, and Yang 2005; Yu, Tresp, and Schwaighofer 2005), and feature representations (Argyriou, Evgeniou, and Pontil 2008; Liu, Ji, and…”
Learning Multiple Tasks using Manifold Regularization (2010, background): “There is also a large body of work on multitask learning that find the shared structure in the tasks using Bayesian inference [23] [24] [9], which in spirit, is similar to the above approaches, but done in a Bayesian way.”
Multitask Compressive Sensing (2009, background): “Typical approaches to information sharing among tasks include: sharing hidden nodes in neural networks [24], [25], placing a common prior in hierarchical Bayesian models [26]–[28], sharing a common structure on the predictor space [29], and structured regularization in kernel methods [30], among oth”