Learning With Single-Teacher Multi-Student

Authors

  • Shan You Peking University
  • Chang Xu University of Sydney
  • Chao Xu Peking University
  • Dacheng Tao University of Sydney

Keywords:

multiclass classification, binary classification, teacher student

Abstract

In this paper we study a new learning problem defined as "Single-Teacher Multi-Student" (STMS) problem, which investigates how to learn a series of student (simple and specific) models from a single teacher (complex and universal) model. Taking the multiclass and binary classification for example, we focus on learning multiple binary classifiers from a single multiclass classifier, where each of binary classifier is responsible for a certain class. This actually derives from some realistic problems, such as identifying the suspect based on a comprehensive face recognition system. By treating the already-trained multiclass classifier as the teacher, and multiple binary classifiers as the students, we propose a gated support vector machine (gSVM) as a solution. A series of gSVMs are learned with the help of single teacher multiclass classifier. The teacher's help is two-fold; first, the teacher's score provides the gated values for students' decision; second, the teacher can guide the students to accommodate training examples with different difficulty degrees. Extensive experiments on real datasets validate its effectiveness.

Downloads

Published

2018-04-29

How to Cite

You, S., Xu, C., Xu, C., & Tao, D. (2018). Learning With Single-Teacher Multi-Student. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11636