What Knowledge Gets Distilled in Knowledge Distillation?
This addresses a fundamental gap in understanding for the machine learning community, though it is incremental as it builds on existing distillation techniques.
The paper investigates what specific knowledge is transferred from teacher to student networks in knowledge distillation, beyond just task performance improvements, and shows that existing methods can indirectly distill properties like object localization and adversarial vulnerability.
Knowledge distillation aims to transfer useful information from a teacher network to a student network, with the primary goal of improving the student's performance for the task at hand. Over the years, there has a been a deluge of novel techniques and use cases of knowledge distillation. Yet, despite the various improvements, there seems to be a glaring gap in the community's fundamental understanding of the process. Specifically, what is the knowledge that gets distilled in knowledge distillation? In other words, in what ways does the student become similar to the teacher? Does it start to localize objects in the same way? Does it get fooled by the same adversarial samples? Does its data invariance properties become similar? Our work presents a comprehensive study to try to answer these questions. We show that existing methods can indeed indirectly distill these properties beyond improving task performance. We further study why knowledge distillation might work this way, and show that our findings have practical implications as well.