- TL;DR: We study whether and how adaptive data augmentation and knowledge distillation can be leveraged simultaneously in a synergistic manner for better training student networks.
- Abstract: Knowledge Distillation (KD) is a common method for transferring the ``knowledge'' learned by one machine learning model (the teacher) into another model (the student), where typically, the teacher has a greater capacity (e.g., more parameters or higher bit-widths). To our knowledge, existing methods overlook the fact that although the student absorbs extra knowledge from the teacher, both models share the same input data -- and this data is the only medium by which the teacher's knowledge can be demonstrated. Due to the difference in model capacities, the student may not benefit fully from the same data points on which the teacher is trained. On the other hand, a human teacher may demonstrate a piece of knowledge with individualized examples adapted to a particular student, for instance, in terms of her cultural background and interests. Inspired by this behavior, we design data augmentation agents with distinct roles to facilitate knowledge distillation. Our data augmentation agents generate distinct training data for the teacher and student, respectively. We focus specifically on KD when the teacher network has greater precision (bit-width) than the student network. We find empirically that specially tailored data points enable the teacher's knowledge to be demonstrated more effectively to the student. We compare our approach with existing KD methods on training popular neural architectures and demonstrate that role-wise data augmentation improves the effectiveness of KD over strong prior approaches. The code for reproducing our results will be made publicly available.
- Code: http://bit.ly/2n0WkDj
- Keywords: Data Augmentation, Knowledge Distillation
- Original Pdf: pdf