Adversarial Partial Multi-Label Learning with Label Disambiguation

Authors

  • Yan Yan Northwestern Polytechnical University
  • Yuhong Guo Carleton University

Keywords:

Classification and Regression

Abstract

Partial multi-label learning (PML), which tackles the problem of learning multi-label prediction models from instances with overcomplete noisy annotations, has recently started gaining attention from the research community. In this paper, we propose a novel adversarial learning model, PML-GAN, under a generalized encoder-decoder framework for partial multi-label learning. The PML-GAN model uses a disambiguation network to identify irrelevant labels and uses a multi-label prediction network to map the training instances to their disambiguated label vectors, while deploying a generative adversarial network as an inverse mapping from label vectors to data samples in the input feature space. The learning of the overall model corresponds to a minimax adversarial game, which enhances the correspondence of input features with the output labels in a bi-directional mapping. Extensive experiments are conducted on both synthetic and real-world partial multi-label datasets, while the proposed model demonstrates the state-of-the-art performance.

Downloads

Published

2021-05-18

How to Cite

Yan, Y., & Guo, Y. (2021). Adversarial Partial Multi-Label Learning with Label Disambiguation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(12), 10568-10576. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17264

Issue

Section

AAAI Technical Track on Machine Learning V