Teaching-to-Learn and Learning-to-Teach for Multi-label Propagation

Authors

  • Chen Gong Shanghai Jiao Tong University and University of Technology Sydney
  • Dacheng Tao University of Technology Sydney
  • Jie Yang Shanghai Jiao Tong University
  • Wei Liu Didi Research, Beijing, China

DOI:

https://doi.org/10.1609/aaai.v30i1.10191

Abstract

Multi-label propagation aims to transmit the multi-label information from labeled examples to unlabeled examples based on a weighted graph. Existing methods ignore the specific propagation difficulty of different unlabeled examples and conduct the propagationin an imperfect sequence, leading to the error-prone classification of some difficult examples with uncertain labels. To address this problem, this paper associates each possible label with a "teacher", and proposesa "Multi-Label Teaching-to-Learn and Learning-to-Teach" (ML-TLLT) algorithm, so that the entire propagationprocess is guided by the teachers and manipulated from simple examples to more difficult ones. In the teaching-to-learn step, the teachers select the simplest examples for the current propagation by investigating both the definitiveness of each possible label of the unlabeled examples, and the dependencies between labels revealed by the labeled examples. In the learning-to-teach step, the teachers reversely learn from the learner’s feedback to properly select the simplest examples for the next propagation. Thorough empirical studies show that due to the optimized propagation sequence designed by the teachers, ML-TLLT yields generally better performance than seven state-of-the-art methods on the typical multi-label benchmark datasets.

Downloads

Published

2016-02-21

How to Cite

Gong, C., Tao, D., Yang, J., & Liu, W. (2016). Teaching-to-Learn and Learning-to-Teach for Multi-label Propagation. Proceedings of the AAAI Conference on Artificial Intelligence, 30(1). https://doi.org/10.1609/aaai.v30i1.10191

Issue

Section

Technical Papers: Machine Learning Methods