Dual Relation Semi-Supervised Multi-Label Learning


  • Lichen Wang Northeastern University
  • Yunyu Liu Northeastern University
  • Can Qin Northeastern University
  • Gan Sun Northeastern University
  • Yun Fu Northeastern University




Multi-label learning (MLL) solves the problem that one single sample corresponds to multiple labels. It is a challenging task due to the long-tail label distribution and the sophisticated label relations. Semi-supervised MLL methods utilize a small-scale labeled samples and large-scale unlabeled samples to enhance the performance. However, these approaches mainly focus on exploring the data distribution in feature space while ignoring mining the label relation inside of each instance. To this end, we proposed a Dual Relation Semi-supervised Multi-label Learning (DRML) approach which jointly explores the feature distribution and the label relation simultaneously. A dual-classifier domain adaptation strategy is proposed to align features while generating pseudo labels to improve learning performance. A relation network is proposed to explore the relation knowledge. As a result, DRML effectively explores the feature-label and label-label relations in both labeled and unlabeled samples. It is an end-to-end model without any extra knowledge. Extensive experiments illustrate the effectiveness and efficiency of our method1.




How to Cite

Wang, L., Liu, Y., Qin, C., Sun, G., & Fu, Y. (2020). Dual Relation Semi-Supervised Multi-Label Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 6227-6234. https://doi.org/10.1609/aaai.v34i04.6089



AAAI Technical Track: Machine Learning