Optimal Margin Distribution Machine for Multi-Instance Learning

Multi-instance learning (MIL) is a celebrated learning framework where each example is represented as a bag of instances. An example is negative if it has no positive instances, and vice versa if at least one positive instance is contained. During the past decades, various MIL algorithms have been proposed, among which the large margin based methods is a very popular class. Recently, the studies on margin theory disclose that the margin distribution is of more importance to generalization ability than the minimal margin. Inspired by this observation, we propose the multi-instance optimal margin distribution machine, which can identify the key instances via explicitly optimizing the margin distribution. We also extend a stochastic accelerated mirror prox method to solve the formulated minimax problem. Extensive experiments show the superiority of the proposed method.

Authors

• Teng Zhang Institute of Computing Technology, Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing Key Laboratory of Mobile Computing and Pervasive Device
• Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab, School of Computer Science and Technology, HUST

Keywords

• Machine Learning: Classification
• Machine Learning: Multi-instance; Multi-label; Multi-view learning