Online Learning of Multiple Tasks and Their Relationships

We propose an Online MultiTask Learning (Omtl) framework which simultaneously learns the task weight vectors as well as the task relatedness adaptively from the data. Our work is in contrast with prior work on online multitask learning which assumes fixed task relatedness, a priori. Furthermore, whereas prior work in such settings assume only positively correlated tasks, our framework can capture negative correlations as well. Our proposed framework learns the task relationship matrix by framing the objective function as a Bregman divergence minimization problem for positive definite matrices. Subsequently, we exploit this adaptively learned task-relationship matrix to select the most informative samples in an online multitask active learning setting. Experimental results on a number of real-world datasets and comparisons with numerous baselines establish the efficacy of our proposed approach.

[1]  Per-Gunnar Martinsson,et al.  Randomized algorithms for the low-rank approximation of matrices , 2007, Proceedings of the National Academy of Sciences.

[2]  Rich Caruana,et al.  Multitask Learning , 1998, Encyclopedia of Machine Learning and Data Mining.

[3]  Peter L. Bartlett,et al.  Matrix regularization techniques for online multitask learning , 2008 .

[4]  Inderjit S. Dhillon,et al.  Low-Rank Kernel Learning with Bregman Matrix Divergences , 2009, J. Mach. Learn. Res..

[5]  John Blitzer,et al.  Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification , 2007, ACL.

[6]  Gábor Lugosi,et al.  Prediction, learning, and games , 2006 .

[7]  Claudio Gentile,et al.  Linear Algorithms for Online Multitask Classification , 2010, COLT.

[8]  Charles A. Micchelli,et al.  Learning Multiple Tasks with Kernel Methods , 2005, J. Mach. Learn. Res..

[9]  Hal Daumé,et al.  Infinite Predictor Subspace Models for Multitask Learning , 2010, AISTATS.

[10]  Koby Crammer,et al.  Adaptive regularization of weight vectors , 2009, Machine Learning.

[11]  Rajat Raina,et al.  Constructing informative priors using transfer learning , 2006, ICML.

[12]  Claudio Gentile,et al.  Worst-Case Analysis of Selective Sampling for Linear Classification , 2006, J. Mach. Learn. Res..

[13]  Lawrence Carin,et al.  Multi-Task Learning for Classification with Dirichlet Process Priors , 2007, J. Mach. Learn. Res..

[14]  Philip M. Long,et al.  Online Multitask Learning , 2006, COLT.

[15]  Gábor Lugosi,et al.  Online Multi-task Learning with Hard Constraints , 2009, COLT.

[16]  Hal Daumé,et al.  Bayesian Multitask Learning with Latent Hierarchies , 2009, UAI.

[17]  Edwin V. Bonilla,et al.  Multi-task Gaussian Process Prediction , 2007, NIPS.

[18]  Gunnar Rätsch,et al.  Matrix Exponentiated Gradient Updates for On-line Learning and Bregman Projection , 2004, J. Mach. Learn. Res..

[19]  Tom Heskes,et al.  Empirical Bayes for Learning to Learn , 2000, ICML.

[20]  Dit-Yan Yeung,et al.  A Convex Formulation for Learning Task Relationships in Multi-Task Learning , 2010, UAI.

[21]  Peter L. Bartlett,et al.  Multitask Learning with Expert Advice , 2007, COLT.