An Extended Kernel for Generalized Multiple-Instance Learning

Authors

Qingping Tao, University of Nebraska-LincolnFollow
Stephen Scott, University of Nebraska-LincolnFollow
N. V. Vinodchandran, University of Nebraska-LincolnFollow
Thomas Takeo Osugi, University of Nebraska-LincolnFollow
Brandon Mueller, University of Nebraska-LincolnFollow

Date of this Version

2004

Comments

Published in 16th IEEE International Conference on Tools with Artificial Intelligence, 2004. ICTAI 2004. Copyright 2004 IEEE. Used by permission.

Abstract

The multiple-instance learning (MIL) model has been successful in areas such as drug discovery and content-based image-retrieval. Recently, this model was generalized and a corresponding kernel was introduced to learn generalized MIL concepts with a support vector machine. While this kernel enjoyed empirical success, it has limitations in its representation. We extend this kernel by enriching its representation and empirically evaluate our new kernel on data from content-based image retrieval, biological sequence analysis, and drug discovery. We found that our new kernel generalized noticeably better than the old one in content-based image retrieval and biological sequence analysis and was slightly better or even with the old kernel in the other applications, showing that an SVM using this kernel does not overfit despite its richer representation.