Improved Knowledge Distillation via Teacher Assistant


  • Seyed Iman Mirzadeh Washington State University
  • Mehrdad Farajtabar DeepMind
  • Ang Li DeepMind
  • Nir Levine DeepMind
  • Akihiro Matsukawa D.E. Shaw
  • Hassan Ghasemzadeh Washington State University



Despite the fact that deep neural networks are powerful models and achieve appealing results on many tasks, they are too large to be deployed on edge devices like smartphones or embedded sensor nodes. There have been efforts to compress these networks, and a popular method is knowledge distillation, where a large (teacher) pre-trained network is used to train a smaller (student) network. However, in this paper, we show that the student network performance degrades when the gap between student and teacher is large. Given a fixed student network, one cannot employ an arbitrarily large teacher, or in other words, a teacher can effectively transfer its knowledge to students up to a certain size, not smaller. To alleviate this shortcoming, we introduce multi-step knowledge distillation, which employs an intermediate-sized network (teacher assistant) to bridge the gap between the student and the teacher. Moreover, we study the effect of teacher assistant size and extend the framework to multi-step distillation. Theoretical analysis and extensive experiments on CIFAR-10,100 and ImageNet datasets and on CNN and ResNet architectures substantiate the effectiveness of our proposed approach.




How to Cite

Mirzadeh, S. I., Farajtabar, M., Li, A., Levine, N., Matsukawa, A., & Ghasemzadeh, H. (2020). Improved Knowledge Distillation via Teacher Assistant. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 5191-5198.



AAAI Technical Track: Machine Learning