Research

Auxiliary Task Reweighting for Minimum-data Learning

NeurIPS

Authors

  • Baifeng Shi
  • Judy Hoffman
  • Kate Saenko
  • Trevor Darrell
  • Huijuan Xu

Published on

10/16/2020

Categories

NeurIPS

Supervised learning requires a large amount of training data, limiting its application where labeled data is scarce. To compensate for data scarcity, one possible method is to utilize auxiliary tasks to provide additional supervision for the main task. Assigning and optimizing the importance weights for different auxiliary tasks remains an crucial and largely understudied research question. In this work, we propose a method to automatically reweight auxiliary tasks in order to reduce the data requirement on the main task. Specifically, we formulate the weighted likelihood function of auxiliary tasks as a surrogate prior for the main task. By adjusting the auxiliary task weights to minimize the divergence between the surrogate prior and the true prior of the main task, we obtain a more accurate prior estimation, achieving the goal of minimizing the required amount of training data for the main task and avoiding a costly grid search. In multiple experimental settings (e.g. semi-supervised learning, multi-label classification), we demonstrate that our algorithm can effectively utilize limited labeled data of the main task with the benefit of auxiliary tasks compared with previous task reweighting methods. We also show that under extreme cases with only a few extra examples (e.g. few-shot domain adaptation), our algorithm results in significant improvement over the baseline.

This paper has been published as a poster at the 2020 Neural Information Processing Systems (NeurIPS) conference.

Please cite our work using the BibTeX below.

@misc{shi2020auxiliary,
      title={Auxiliary Task Reweighting for Minimum-data Learning}, 
      author={Baifeng Shi and Judy Hoffman and Kate Saenko and Trevor Darrell and Huijuan Xu},
      year={2020},
      eprint={2010.08244},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}
Close Modal