Decomposition-Based Evolutionary Multiobjective Optimization to Self-Paced Learning

Self-paced learning (SPL) is a recently proposed paradigm to imitate the learning process of humans/animals. SPL involves easier samples into training at first and then gradually takes more complex ones into consideration. Current SPL regimes incorporate a self-paced (SP) regularizer into the learning objective with a gradually increasing pace parameter. Therefore, it is difficult to obtain the solution path of the SPL regime and determine where to optimally stop this increasing process. In this paper, a multiobjective SPL method is proposed to optimize the loss function and the SP regularizer simultaneously. A decomposition-based multiobjective particle swarm optimization algorithm is used to simultaneously optimize the two objectives for obtaining the solutions. In the proposed method, a polynomial soft weighting regularizer is proposed to penalize the loss. Theoretical studies are conducted to show that the previous regularizers are roughly particular cases of the proposed polynomial soft weighting regularizer family. Then an implicit decomposition method is proposed to search the solutions with respect to the sample number involved into training. A set of solutions can be obtained by the proposed method and naturally constitute the solution path of the SPL regime. Then a satisfactory solution can be naturally obtained from these solutions by utilizing some effective tools in evolutionary multiobjective optimization. Experiments on matrix factorization and classification problems demonstrate the effectiveness of the proposed technique.

[1]  Kaisa Miettinen,et al.  Nonlinear multiobjective optimization , 1998, International series in operations research and management science.

[2]  Carlos A. Coello Coello,et al.  Evolutionary multi-objective optimization: a historical view of the field , 2006, IEEE Comput. Intell. Mag..

[3]  Shuicheng Yan,et al.  Practical low-rank matrix approximation under robust L1-norm , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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

[5]  Lianru Gao,et al.  Endmember Extraction of Hyperspectral Remote Sensing Images Based on the Discrete Particle Swarm Optimization Algorithm , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Lei Zhang,et al.  A Cyclic Weighted Median Method for L1 Low-Rank Matrix Factorization with Missing Entries , 2013, AAAI.

[7]  Deva Ramanan,et al.  Self-Paced Learning for Long-Term Tracking , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

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

[9]  Rubén González Crespo,et al.  MOVPSO: Vortex Multi-Objective Particle Swarm Optimization , 2017, Appl. Soft Comput..

[10]  Yang Yu,et al.  On Constrained Boolean Pareto Optimization , 2015, IJCAI.

[11]  R. K. Ursem.  Multi-objective Optimization using Evolutionary Algorithms , 2009 .

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

[13]  Cordelia Schmid,et al.  Actions in context , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Florent Perronnin,et al.  Fisher Kernels on Visual Vocabularies for Image Categorization , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Ying Lin,et al.  Particle Swarm Optimization With an Aging Leader and Challengers , 2013, IEEE Transactions on Evolutionary Computation.

[16]  Deyu Meng,et al.  Robust Matrix Factorization with Unknown Noise , 2013, 2013 IEEE International Conference on Computer Vision.

[17]  Tommi S. Jaakkola,et al.  Weighted Low-Rank Approximations , 2003, ICML.

[18]  Fei-Fei Li,et al.  Shifting Weights: Adapting Object Detectors from Image to Video , 2012, NIPS.

[19]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

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

[21]  Kalyanmoy Deb,et al.  Finding Knees in Multi-objective Optimization , 2004, PPSN.

[22]  Xin Yao,et al.  On the approximation ability of evolutionary optimization with application to minimum set cover , 2010, Artif. Intell..

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

[24]  Takayuki Okatani,et al.  Efficient algorithm for low-rank matrix factorization with missing components and performance comparison of latest algorithms , 2011, 2011 International Conference on Computer Vision.

[25]  Deyu Meng,et al.  A theoretical understanding of self-paced learning , 2017, Inf. Sci..

[26]  Bilge Mutlu,et al.  How Do Humans Teach: On Curriculum Learning and Teaching Dimension , 2011, NIPS.

[27]  K. Deb,et al.  Understanding knee points in bicriteria problems and their implications as preferred solution principles , 2011 .

[28]  Yang Yu,et al.  Pareto Ensemble Pruning , 2015, AAAI.

[29]  Bernhard Sendhoff,et al.  Pareto-Based Multiobjective Machine Learning: An Overview and Case Studies , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[30]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[31]  Mengjie Zhang,et al.  Particle Swarm Optimization for Feature Selection in Classification: A Multi-Objective Approach , 2013, IEEE Transactions on Cybernetics.

[32]  Andrew W. Fitzgibbon,et al.  Damped Newton algorithms for matrix factorization with missing data , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[33]  Daphne Koller,et al.  Learning specific-class segmentation from diverse data , 2011, 2011 International Conference on Computer Vision.

[34]  Maoguo Gong,et al.  Complex Network Clustering by Multiobjective Discrete Particle Swarm Optimization Based on Decomposition , 2014, IEEE Transactions on Evolutionary Computation.

[35]  Gary B. Lamont,et al.  Evolutionary Algorithms for Solving Multi-Objective Problems , 2002, Genetic Algorithms and Evolutionary Computation.

[36]  Yang Gao,et al.  Self-paced dictionary learning for image classification , 2012, ACM Multimedia.

[37]  Alexander G. Hauptmann,et al.  Leveraging high-level and low-level features for multimedia event detection , 2012, ACM Multimedia.

[38]  Maoguo Gong,et al.  Multi-Objective Self-Paced Learning , 2016, AAAI.

[39]  Wang Hu,et al.  Adaptive Multiobjective Particle Swarm Optimization Based on Parallel Cell Coordinate System , 2015, IEEE Transactions on Evolutionary Computation.

[40]  Deyu Meng,et al.  Easy Samples First: Self-paced Reranking for Zero-Example Multimedia Search , 2014, ACM Multimedia.

[41]  M Reyes Sierra,et al.  Multi-Objective Particle Swarm Optimizers: A Survey of the State-of-the-Art , 2006 .

[42]  Qingfu Zhang,et al.  MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition , 2007, IEEE Transactions on Evolutionary Computation.

[43]  Sotirios Chatzis.  Dynamic Bayesian Probabilistic Matrix Factorization , 2014, AAAI.

[44]  Sumit Basu,et al.  Teaching Classification Boundaries to Humans , 2013, AAAI.

[45]  Shiguang Shan,et al.  Self-Paced Curriculum Learning , 2015, AAAI.

[46]  Xin Yao,et al.  An Evolutionary Multiobjective Approach to Sparse Reconstruction , 2014, IEEE Transactions on Evolutionary Computation.

[47]  Ganesh K. Venayagamoorthy,et al.  Particle Swarm Optimization in Wireless-Sensor Networks: A Brief Survey , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[48]  Takeo Kanade,et al.  Robust L/sub 1/ norm factorization in the presence of outliers and missing data by alternative convex programming , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[49]  Yasuo Matsuyama.  Harmonic competition: a self-organizing multiple criteria optimization , 1996, IEEE Trans. Neural Networks.

[50]  Jing J. Liang,et al.  A Multiobjective Particle Swarm Optimizer Using Ring Topology for Solving Multimodal Multiobjective Problems , 2018, IEEE Transactions on Evolutionary Computation.

[51]  Yang Yu,et al.  Subset Selection by Pareto Optimization , 2015, NIPS.

[52]  Carlos A. Coello Coello,et al.  Handling multiple objectives with particle swarm optimization , 2004, IEEE Transactions on Evolutionary Computation.

[53]  Takeo Kanade,et al.  Shape and motion from image streams under orthography: a factorization method , 1992, International Journal of Computer Vision.

[54]  Alexander G. Hauptmann,et al.  Temporal Extension of Scale Pyramid and Spatial Pyramid Matching for Action Recognition , 2014, ArXiv.

[55]  Jun Zhang,et al.  A Novel Set-Based Particle Swarm Optimization Method for Discrete Optimization Problems , 2010, IEEE Transactions on Evolutionary Computation.