Adversary Is the Best Teacher: Towards Extremely Compact Neural Networks

Abstract

With neural networks rapidly becoming deeper, there emerges a need for compact models. One popular approach for this is to train small student networks to mimic larger and deeper teacher models, rather than directly learn from the training data. We propose a novel technique to train student-teacher networks without directly providing label information to the student. However, our main contribution is to learn how to learn from the teacher by a unique strategy---having the student compete with a discriminator.

Cite

Text

Prabhu et al. "Adversary Is the Best Teacher: Towards Extremely Compact Neural Networks." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.12182

Markdown

[Prabhu et al. "Adversary Is the Best Teacher: Towards Extremely Compact Neural Networks." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/prabhu2018aaai-adversary/) doi:10.1609/AAAI.V32I1.12182

BibTeX

@inproceedings{prabhu2018aaai-adversary,
  title     = {{Adversary Is the Best Teacher: Towards Extremely Compact Neural Networks}},
  author    = {Prabhu, Ameya and Krishna, Harish and Saha, Soham},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {8137-8138},
  doi       = {10.1609/AAAI.V32I1.12182},
  url       = {https://mlanthology.org/aaai/2018/prabhu2018aaai-adversary/}
}