Feature Selection in Multi-instance Learning ∗

This paper focuses on the feature selection in multi-instance learning. A new version of support vector machine named p-MISVM is proposed. In the p-MISVM model, the problem needs to be solved is non-differentiable and non-convex. By using the constrained concave-convex procedure (CCCP), a linearization algorithm is presented that solves a succession of fast linear programs that converges to a local optimal solution. Furthermore, the lower bounds for the absolute value of nonzero components in every local optimal solution is established, which can eliminate zero components in any numerical solution. The numerical experiments show that the p-MISVM is effective in selecting relevant features, compared with the popular MICA.

[1]  Thomas G. Dietterich,et al.  Solving the Multiple Instance Problem with Axis-Parallel Rectangles , 1997, Artif. Intell..

[2]  Tomás Lozano-Pérez,et al.  A Framework for Multiple-Instance Learning , 1997, NIPS.

[3]  Paul S. Bradley,et al.  Feature Selection via Concave Minimization and Support Vector Machines , 1998, ICML.

[4]  Jun Wang,et al.  Solving the Multiple-Instance Problem: A Lazy Learning Approach , 2000, ICML.

[5]  Thomas Hofmann,et al.  Support Vector Machines for Multiple-Instance Learning , 2002, NIPS.

[6]  Alan L. Yuille,et al.  The Concave-Convex Procedure , 2003, Neural Computation.

[7]  Xin Xu,et al.  Logistic Regression and Boosting for Labeled Bags of Instances , 2004, PAKDD.

[8]  Thomas Hofmann,et al.  Kernel Methods for Missing Variables , 2005, AISTATS.

[9]  Paul A. Viola,et al.  Multiple Instance Boosting for Object Detection , 2005, NIPS.

[10]  Mark Craven,et al.  Multiple-Instance Active Learning , 2007, NIPS.

[11]  Thomas Hofmann,et al.  Multiple Instance Learning for Computer Aided Diagnosis , 2007 .

[12]  Edward W. Wild,et al.  Multiple Instance Classification via Successive Linear Programming , 2008 .

[13]  Y. Ye,et al.  Lower Bound Theory of Nonzero Entries in Solutions of ℓ2-ℓp Minimization , 2010, SIAM J. Sci. Comput..

[14]  Nai-Yang Deng,et al.  Cancer Related Gene Identification via p-norm Support Vector Machine ∗ , 2010 .

[15]  Jian Yin,et al.  Feature selection in multi-instance learning , 2012, Neural Computing and Applications.