弹性多核学习
doi: 10.3724/SP.J.1004.2011.00693
Elastic Multiple Kernel Learning
-
摘要: 多核学习 (MKL) 的提出是为了解决多个核矩阵的融合问题, 多核学习求解关于多个核矩阵的最优的线性组合并同时解出对应于这个组合矩阵的支持向量机(SVM)问题. 现有的多核学习的框架倾向于寻找稀疏的组合系数, 但是当有信息的核的比例较高的时候, 对稀疏性的倾向会使得只有少量的核被选中而损失相当的分类信息. 在本文中, 我们提出了弹性多核学习的框架来实现自适应的多核学习. 弹性多核学习的框架利用了一个混合正则化函数来均衡稀疏性和非稀疏性, 多核学习和支持向量机问题都可以视作弹性多核学习的特殊情形. 基于针对多核学习的梯度下降法, 我们导出了针对弹性多核学习的梯度下降法. 仿真数据的结果显示了弹性多核学习方法相对多核学习和支持向量机的优势; 我们还进一步将弹性多核学习应用于基因集合分析问题并取得了有意义的结果; 最后, 我们比较研究了弹性多核学习与另一种利用了非稀疏思想的多核学习.Abstract: Multiple kernel learning (MKL) was proposed to deal with kernel fusion. MKL learns a linear combination of several kernels and solves the supporting vector machine (SVM) associated with the combined kernel simultaneously. Current framework of MKL encourages sparsity of the kernel combination coefficients. When a significant portion of the kernels are informative, forcing sparsity tends to select only a few kernels and may ignore useful information. In this paper, we propose elastic multiple kernel learning (EMKL) to achieve adaptive kernel fusion. EMKL makes use of a mixing regularization function to compromise sparsity and non-sparsity. Both MKL and SVM could be regarded as special cases of EMKL. Based on gradient descent algorithm for MKL problem, we propose a fast algorithm to solve EMKL problem. Results on the simulation datasets demonstrate that the performance of EMKL compares favorably to both MKL and SVM. We further apply EMKL to gene set analysis and get promising results. Finally, we study the theoretical advantage of EMKL comparing to other non-sparse MKL.
-
[1] Bonnans J F, Gilbert J C, Lemarechal C, Sagastizabal C. Numerical Optimization: Theoretical and Practical Aspects. Springer-Verlag, 2006[2] Lanckriet G R G, Cristianini N, Bartlett P, Ghaoui L E, Jordan M I. Learning the kernel matrix with semidefinite programming. Journal of Machine Learning Research, 2004, 5. 27-72[3] Bach F R, Lanckriet G R G, Jordan M I. Multiple kernel learning, conic duality, and the SMO algorithm. In: Proceedings of the 21st International Conference on Machine Learning. New York, USA: ACM 2004. 1-8[4] Kimeldor G S, Wahba G. Some results on tchebycheffian spline functions. Journal of Mathematical Analysis and Applications, 1971, 33(1): 82-95 [5] Schlkopf B, Smola A. Learning with kernels: support vector machines, regularization, optimization, and beyond. Cambridge: The MIT Press, 2002[6] Tibshirani R. Regression shrinkage and selection via the Lasso. Journal of the Royal Statistical Society Series B-Statistical Methodology, 1996, 58(1): 267-288[7] Zou H, Hastie T. Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society Series B-Statistical Methodology, 2005, 67: 301-320[8] Micchelli C A, Pontil M. Learning the kernel function via regularization. Journal of Machine Learning Research, 2005, 6: 1099-1125[9] Rakotomamonjy A, Bach F R, Canu S, Grandvalet Y. SimpleMKL. Journal of Machine Learning Research, 2008, 9: 2491-2521[10] Bonnans J F, Shapiro A. Optimization problems with perturbations: A guided tour. Siam Review, 1998, 40(2): 228-264[11] Sturm J F. Using SeDuMi 1.02, a MATLAB toolbox for optimization over symmetric cones. Optimization Methods Software, 1999, 11: 625-653[12] Hess K R, Anderson K, Symmans W F, Valero V, Ibrahim N, Mejia J, et al. Pharmacogenomic predictor of sensitivity to preoperative chemotherapy with paclitaxel and fluorouracil, doxorubicin, and cyclophosphamide in breast cancer. Journal of Clinical Oncology, 2006, 24(26): 4236-4244[13] Fumoleau P, Campone M, Coudert B, Mayer F, Favier L, Ferrant E. Targeting ErbB receptors in breast cancer. Bullitin du Cancer, 2007, 94, F147-170[14] Bando H. Vascular endothelial growth factor and bevacitumab in breast cancer. Breast Cancer, 2007, 14(2): 163-173[15] Buck M B, Knabbe C. TGF-beta signaling in breast cancer. Annals of the New York Academy of Sciences, 2006, , 119-126[16] Hancox R A, Allen M D, Holliday D L, Edwards D R, Pennington C, Guttery D S, et al. Tumour-associated tenascin-C isoforms promote breast cancer cell invasion and growth by matrix metalloproteinase-dependent and independent mechanisms. Breast Cancer Research, 2009, 11(2): 1-13[17] Ilvesaro J M, Merrell M A, Li L, Wakchoure S, Graves D, Brooks S, et al. Toll-like receptor 9 mediates CpG oligonucleotide-induced cellular invasion. Molecular Cancer Research, 2008, (10): 1534-1543[18] Jing J, Tarbutton E, Wilson G, Prekeris R. Rab11-FIP3 is a Rab11-binding protein that regulates breast cancer cell motility by modulating the actin cytoskeleton. European Journal of Cell Biology, 2009, 88(6): 325-341[19] Kloft M, Brefeld U, Laskov P, Sonnenburg S. Non-sparse multiple kernel learning. In: Proceedings of the Neural Information Processing Systems Workshop Vancouver, Canada: Curran Associatos, 2008. 1-4[20] Efron B, Hastie T, Johnstone I, Tibshirani R. Least angle regression. Annals of Statistics, 2004, 32(2): 407-451
点击查看大图
计量
- 文章访问数: 2243
- HTML全文浏览量: 55
- PDF下载量: 991
- 被引次数: 0