ICML 2020poster10 citations

Extreme Multi-label Classification from Aggregated Labels

Yanyao Shen, Hsiang-Fu Yu, Sujay Sanghavi, Inderjit Dhillon

Abstract

Extreme multi-label classification (XMC) is the problem of finding the relevant labels for an input, from a very large universe of possible labels. We consider XMC in the setting where labels are available only for groups of samples - but not for individual ones. Current XMC approaches are not built for such multi-instance multi-label (MIML) training data, and MIML approaches do not scale to XMC sizes. We develop a new and scalable algorithm to impute individual-sample labels from the group labels; this can be paired with any existing XMC method to solve the aggregated label problem. We characterize the statistical properties of our algorithm under mild assumptions, and provide a new end-to-end framework for MIML as an extension. Experiments on both aggregated label XMC and MIML tasks show the advantages over existing approaches.

BibTeX
@InProceedings{pmlr-v119-shen20f,
  title = 	 {Extreme Multi-label Classification from Aggregated Labels},
  author =       {Shen, Yanyao and Yu, Hsiang-Fu and Sanghavi, Sujay and Dhillon, Inderjit},
  booktitle = 	 {Proceedings of the 37th International Conference on Machine Learning},
  pages = 	 {8752--8762},
  year = 	 {2020},
  editor = 	 {III, Hal Daumé and Singh, Aarti},
  volume = 	 {119},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {13--18 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v119/shen20f/shen20f.pdf},
  url = 	 {https://proceedings.mlr.press/v119/shen20f.html},
  abstract = 	 {Extreme multi-label classification (XMC) is the problem of finding the relevant labels for an input, from a very large universe of possible labels. We consider XMC in the setting where labels are available only for groups of samples - but not for individual ones. Current XMC approaches are not built for such multi-instance multi-label (MIML) training data, and MIML approaches do not scale to XMC sizes. We develop a new and scalable algorithm to impute individual-sample labels from the group labels; this can be paired with any existing XMC method to solve the aggregated label problem. We characterize the statistical properties of our algorithm under mild assumptions, and provide a new end-to-end framework for MIML as an extension. Experiments on both aggregated label XMC and MIML tasks show the advantages over existing approaches.}
}