Incorporating Label Embedding and Feature Augmentation for Multi-Dimensional Classification


  • Haobo Wang Zhejiang University
  • Chen Chen Zhejiang University
  • Weiwei Liu Wuhan University
  • Ke Chen Zhejiang University
  • Tianlei Hu Zhejiang University
  • Gang Chen Zhejiang University



Feature augmentation, which manipulates the feature space by integrating the label information, is one of the most popular strategies for solving Multi-Dimensional Classification (MDC) problems. However, the vanilla feature augmentation approaches fail to consider the intra-class exclusiveness, and may achieve degenerated performance. To fill this gap, a novel neural network based model is proposed which seamlessly integrates the Label Embedding and Feature Augmentation (LEFA) techniques to learn label correlations. Specifically, based on attentional factorization machine, a cross correlation aware network is introduced to learn a low-dimensional label representation that simultaneously depicts the inter-class correlations and the intra-class exclusiveness. Then the learned latent label vector can be used to augment the original feature space. Extensive experiments on seven real-world datasets demonstrate the superiority of LEFA over state-of-the-art MDC approaches.




How to Cite

Wang, H., Chen, C., Liu, W., Chen, K., Hu, T., & Chen, G. (2020). Incorporating Label Embedding and Feature Augmentation for Multi-Dimensional Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 6178-6185.



AAAI Technical Track: Machine Learning