A Dirty Model for Multi-task Learning

By Ali Jalali, Pradeep Ravikumar, Sujay Sanghavi, Chao Ruan. 2010

410 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.

In Statistical Learning Theory

Citations in the corpus

An Overview of Multi-task Learning (2018, methodology): “[53]”
Cross-Stitch Networks for Multi-task Learning (2016, background): “The term multi-task learning (MTL) itself has been broadly used [2, 14, 28, 42, 54, 55] as an umbrella term to include representation learning and selection [4, 13, 31, 37], transfer learning [39, 41, 56] etc.”
A Survey on Multi-Task Learning (2017, methodology): “In [177], similar to [100], a decomposition model with one component modeling low-rank”
Learning Task Grouping and Overlap in Multi-task Learning (2012, methodology): “In (Jalali et al., 2010), this model was reﬁned and features are assumed to be either active for all tasks, or inactive for most of the tasks.”
Deep learning for detecting robotic grasps (2013, methodology): “As in most deep learning works, we use a two-phase learning approach.”
Latent Multi-Task Architecture Learning (2017, background): “ to learn where to split merged networks [21], as well as work trying to learn how best to combine private and shared subspaces [5, 18]. Our model is empirically justiﬁed and deals with the dirtiness [16] of loosely related tasks. We show that it is a generalization of various multi-task learning al”
Distributed Multi-Task Learning (2015, background): “DSML can be easily extended to other types of structured sparsity, including sparse group lasso [Friedman et al., 2010], tree-guided group lasso [Kim and Xing, 2010] and the dirty model [Jalali et al., 2010].”
Sluice networks: Learning what to share between loosely related tasks (2017, methodology): “Our model is empirically justiﬁed and deals with the dirtiness [16] of loosely related tasks.”
Multi-Stage Multi-Task Feature Learning (2012, neutral): “M L ] 2 Keywords: Multi-Task Learning, Multi-Stage, Non-convex, Sparse Learning”
Multi-Task Learning and Algorithmic Stability (2015, methodology): “, (Chen, Liu, and Ye 2010; Jalali et al. 2010; Chen, Zhou, and Ye 2011; Chen, Liu, and Ye 2012; Gong, Ye, and Zhang 2012)) to decompose the model parameters of all tasks into two components which are assumed to pursue some sparse properties.”
Learning Multi-Level Task Groups in Multi-Task Learning (2015, methodology): “and Xu 2010; Zhang and Schneider 2010; Zhang and Yeung 2010; Zhang 2013; Zhang and Yeung 2014), and some assume the task structure is hierarchical (Daumé III 2009; Jalali et al. 2010; Görnitz et al. 2011; Lozano and Swirszcz 2012; Zweig and Weinshall 2013).”
Flexible Clustered Multi-Task Learning by Learning Representative Tasks (2016, methodology): “Dirty MTL [29]: model parameters of all tasks are considered as two parts: the first part is shared by all tasks and the second part represents specific features of each task.”
Learning Tree Structure in Multi-Task Learning (2015, methodology): “We compare the TAT method with several state-of-the-art MTL models, including the multi-task feature learning (MTFL) model [19],(3) the dirty model (Dirty) [15],(3) the Cascade model [28], the clustered multi-task learning (CMTL) model [14],(4) the grouping and overlap MTL (GOMTL) model [18], and th”
Learning Feature Selection Dependencies in Multi-task Learning (2013, methodology): “These methods include the model described in [16] and the model for dirty data proposed in [15].”
No Matter Where You Are: Flexible Graph-Guided Multi-task Learning for Multi-view Head Pose Classification under Target Motion (2013, background): “in the form of a graph) defining task dependencies [6] or learn the task relationships simultaneously with task-specific parameters [11, 24, 10, 25, 9].”