Self-Paced Multi-Task Learning

In this paper, we propose a novel multi-task learning (MTL) framework, called Self-Paced Multi-Task Learning (SPMTL). Different from previous works treating all tasks and instances equally when training, SPMTL attempts to jointly learn the tasks by taking into consideration the complexities of both tasks and instances. This is inspired by the cognitive process of human brain that often learns from the easy to the hard. We construct a compact SPMTL formulation by proposing a new task-oriented regularizer that can jointly prioritize the tasks and the instances. Thus it can be interpreted as a self-paced learner for MTL. A simple yet effective algorithm is designed for optimizing the proposed objective function. An error bound for a simplified formulation is also analyzed theoretically. Experimental results on toy and real-world datasets demonstrate the effectiveness of the proposed approach, compared to the state-of-the-art methods.

[1]  Hal Daumé,et al.  Learning Task Grouping and Overlap in Multi-task Learning , 2012, ICML.

[2]  Daphne Koller,et al.  Self-Paced Learning for Latent Variable Models , 2010, NIPS.

[3]  Junfeng Yang,et al.  A Fast Algorithm for Edge-Preserving Variational Multichannel Image Restoration , 2009, SIAM J. Imaging Sci..

[4]  Jieping Ye,et al.  A convex formulation for learning shared structures from multiple tasks , 2009, ICML '09.

[5]  Qian Xu,et al.  Probabilistic Multi-Task Feature Selection , 2010, NIPS.

[6]  Changsheng Li,et al.  Active Sample Learning and Feature Selection: A Unified Approach , 2015, ArXiv.

[7]  Svetha Venkatesh,et al.  Factorial Multi-Task Learning : A Bayesian Nonparametric Approach , 2013, ICML.

[8]  Paul Tseng,et al.  Trace Norm Regularization: Reformulations, Algorithms, and Multi-Task Learning , 2010, SIAM J. Optim..

[9]  Jiayu Zhou,et al.  Efficient multi-task feature learning with calibration , 2014, KDD.

[10]  Junchi Yan,et al.  Weighted sparse coding residual minimization for visual tracking , 2011, 2011 Visual Communications and Image Processing (VCIP).

[11]  Kristen Grauman,et al.  Learning with Whom to Share in Multi-task Feature Learning , 2011, ICML.

[12]  R. Courant,et al.  Methods of Mathematical Physics , 1962 .

[13]  J. Elman.  Learning and development in neural networks: the importance of starting small , 1993, Cognition.

[14]  Jieping Ye,et al.  Multi-stage multi-task feature learning , 2012, J. Mach. Learn. Res..

[15]  Chao Li,et al.  A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[16]  Xiaogang Wang,et al.  Boosted multi-task learning for face verification with applications to web image and video search , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Shiguang Shan,et al.  Self-Paced Learning with Diversity , 2014, NIPS.

[18]  Eric Eaton,et al.  Active Task Selection for Lifelong Machine Learning , 2013, AAAI.

[19]  Massimiliano Pontil,et al.  Regularized multi--task learning , 2004, KDD.

[20]  Jiayu Zhou,et al.  A multi-task learning formulation for predicting disease progression , 2011, KDD.

[21]  Jing Zhao,et al.  Smart Task Orderings for Active Online Multitask Learning , 2014 .

[22]  Dacheng Tao,et al.  Multi-view Self-Paced Learning for Clustering , 2015, IJCAI.

[23]  Dacheng Tao,et al.  Multi-Task Model and Feature Joint Learning , 2015, IJCAI.

[24]  Jiayu Zhou,et al.  Integrating low-rank and group-sparse structures for robust multi-task learning , 2011, KDD.

[25]  Massimiliano Pontil,et al.  Convex multi-task feature learning , 2008, Machine Learning.

[26]  Chris Buckley,et al.  OHSUMED: an interactive retrieval evaluation and new large test collection for research , 1994, SIGIR '94.

[27]  Xiangyang Xue,et al.  Flexible multi-task learning with latent task grouping , 2016, Neurocomputing.

[28]  Yiming Yang,et al.  Learning Multiple Related Tasks using Latent Independent Component Analysis , 2005, NIPS.

[29]  Dr. M. G. Worster.  Methods of Mathematical Physics , 1947, Nature.

[30]  Jieping Ye,et al.  Multi-Task Feature Learning Via Efficient l2, 1-Norm Minimization , 2009, UAI.

[31]  Christoph H. Lampert,et al.  Curriculum learning of multiple tasks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Anton Schwaighofer,et al.  Learning Gaussian Process Kernels via Hierarchical Bayes , 2004, NIPS.

[33]  Jason Weston,et al.  Curriculum learning , 2009, ICML '09.

[34]  Eunho Yang,et al.  Asymmetric multi-task learning based on task relatedness and loss , 2016, ICML 2016.

[35]  Dit-Yan Yeung,et al.  Transfer metric learning by learning task relationships , 2010, KDD.

[36]  Jun Zhu,et al.  Bayesian Max-margin Multi-Task Learning with Data Augmentation , 2014, ICML.

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

[39]  Xiangyang Xue,et al.  Multiple Task Learning Using Iteratively Reweighted Least Square , 2013, IJCAI.

[40]  Baoxin Li,et al.  Predicting Multiple Attributes via Relative Multi-task Learning , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[41]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[42]  Convex Optimization in Signal Processing and Communications , 2010 .

[43]  Junchi Yan,et al.  Visual Saliency Detection via Sparsity Pursuit , 2010, IEEE Signal Processing Letters.

[44]  Ming Yang,et al.  Multi-Task Learning with Gaussian Matrix Generalized Inverse Gaussian Model , 2013, ICML.

[45]  Jun Wang,et al.  Multiple task learning with flexible structure regularization , 2016, Neurocomputing.

[46]  Eric P. Xing,et al.  Tree-Guided Group Lasso for Multi-Task Regression with Structured Sparsity , 2009, ICML.

[47]  Shengcai Liao,et al.  Large Scale Similarity Learning Using Similar Pairs for Person Verification , 2016, AAAI.

[48]  Marc Teboulle,et al.  Gradient-based algorithms with applications to signal-recovery problems , 2010, Convex Optimization in Signal Processing and Communications.

[49]  Qi Xie,et al.  Self-Paced Learning for Matrix Factorization , 2015, AAAI.

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

[51]  Zhi-Quan Luo,et al.  A Unified Convergence Analysis of Block Successive Minimization Methods for Nonsmooth Optimization , 2012, SIAM J. Optim..

[52]  Shengcai Liao,et al.  Salient Color Names for Person Re-identification , 2014, ECCV.

[53]  Trevor Darrell,et al.  An efficient projection for l1, ∞ regularization , 2009, ICML '09.

[54]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[55]  Pradeep Ravikumar,et al.  A Dirty Model for Multitask Learning ( Appendices ) , 2010 .

[56]  Ali Jalali,et al.  A Dirty Model for Multi-task Learning , 2010, NIPS.

[57]  Tong Zhang,et al.  A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , 2005, J. Mach. Learn. Res..