Multi-task Sparse Structure Learning

Gonçalves, Alim P. C.; Das, Priyanka; Chatterjee, Soumyadeep; Sivakumar, Vidyashankar; Zuben, Fernando J. Von; Banerjee, Arindam

doi:10.1145/2661829.2662091

Cited by 36 publications

(43 citation statements)

References 28 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the different problems are sufficiently related, MTL can lead to better generalization and benefit all of the tasks Evgeniou and Pontil (2004) Goncalves et al (2014) and Zhang and Yeung (2012) propose to jointly learning the task relationship structures and the task parameters without grouping them.…”

Section: Related Workmentioning

confidence: 99%

Mixed bi-subject kinship verification via multi-view multi-task learning

Qin

Tan²,

Chen³

2016

Neurocomputing

View full text Add to dashboard Cite

Bi-subject kinship verification addresses the problem of verifying whether there exists some kind of kin relationship (i.e., father-son, father-daughter, motherson and mother-daughter) between a pair of parent-child subjects based purely on their visual appearance. The task is challenging due to the involvement of two different subjects possibly with different genders and ages. In addition, collecting sufficient training samples for each type of kinship is difficult. In this work, we present a novel method to address these issues by considering each type of kin relation verification as one task and learning them at one time in the framework of multi-task learning, by sharing feature sets and useful structures among the tasks.Particularly our contributions are three folds: first, we introduce a new type of learning problem, called mixed bi-subject kinship verification, to the topic of bi-subject kinship verification: instead of simply verifying whether some fixed kinship relationship (e.g., mother-son) can be established for a given pair of parent-child images, we try to figure out whether any type of the four kinship relations can be established according to the visual features of the image pair, with no need to know the genders of the subjects to be verified beforehand. Second, we propose a novel multi-task learning method to address this problem with two transformation matrices -one is shared amongst all the tasks and the other is unique to each task. Both matrices are simultaneously learned in a joint framework, which enables our algorithm to utilize the common knowledge of the four tasks. Third, we propose a multi-view multi-task learning(MMTL) method to perform multiple feature fusion to improve the mixed bi-subject kinship verification performance. Extensive experiments on the large scale KinFaceW kinship database demonstrate the feasibility and effectiveness of the proposed algorithm.

show abstract

Section: Related Workmentioning

confidence: 99%

Mixed bi-subject kinship verification via multi-view multi-task learning

Qin

Tan²,

Chen³

2016

Neurocomputing

View full text Add to dashboard Cite

show abstract

“…The gradient of (12) w.r.t. W is given by (A * ) ⊤ C. Replacing the Linkage regularizer with the smooth approximation (12), we solve the following optimization problem:…”

Section: Algorithmmentioning

confidence: 99%

“…One thing that is worthy of mentioning here is that Linkage is closely related to Multi-Task Learning (MTL) [2,8,13,12,17,22,24], which is a learning paradigm aiming at learning a problem together with other related problems at the same time, under a shared representation. To the best of our knowledge, most existing multi-task learning methods assume the tasks are homogeneous, i.e., of the same type.…”

Section: Introductionmentioning

confidence: 99%

Linkage

Sun

Wang

2015

Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Comprehensive risk assessment lies in the core of enabling proactive healthcare delivery systems. In recent years, datadriven predictive modeling approaches have been increasingly recognized as promising techniques to help enhance healthcare quality and reduce cost. In this paper, we propose a data-driven comprehensive risk prediction method, named Linkage, which can be used to jointly assess a set of associated risks in support of holistic care management. Our method can not only perform prediction but also discover the relationships among those risks. The advantages of the proposed model include: 1) It can leverage the relationship between risks and domains and achieve better risk prediction performance; 2) It provides a data-driven approach to understand relationship between risks; 3) It leverages the information between risk prediction and risk association learning to regulate the improvement on both parts; 4) It provides flexibility to incorporate domain knowledge in learning risk associations. We validate the effectiveness of the proposed model on synthetic data and a real-world healthcare survey data set.

show abstract

“…This interest comes from studies on data of continuously growing size, complexity, and interconnection. As a consequence, new models have been proposed to deal with multivariate structured data in climatology (Gonçalves et al, ; Gonçalves, Von Zuben, & Banerjee, ; Subbian & Banerjee, ), network analysis (Li, Kailkhura, Thiagarajan, Zhang, & Varshney, ; Han & Zhang, ), feature selection (Huang, Tang, Chen, Ding, & Luo, ), etc.…”

Section: Introductionmentioning

confidence: 99%

Double‐structured sparse multitask regression with application of statistical downscaling

Ding

2018

Environmetrics

View full text Add to dashboard Cite

Statistical learning of high‐dimensional data often improves learning performance by taking advantage of structural information hidden in data. In this paper, we investigate the structured multitask learning problem and propose a generalized estimator to utilize the structural information simultaneously from the predictors and from the response variables. The key idea of our methodology is to apply flexible quadratic penalties to regularize the likelihood function that incorporates both types of structural information. We prove the theoretical statistical properties of the proposed estimator, which generalizes several state‐of‐the‐art sparse learning methods. Numerical examples are provided for the proposed estimator on synthetic data and on the statistical downscaling problem in climate research.

show abstract

Multi-task Sparse Structure Learning

Cited by 36 publications

References 28 publications

Mixed bi-subject kinship verification via multi-view multi-task learning

Mixed bi-subject kinship verification via multi-view multi-task learning

Linkage

Double‐structured sparse multitask regression with application of statistical downscaling

Contact Info

Product

Resources

About