Skip to yearly menu bar Skip to main content

In-Person Poster presentation / poster accept

Scaffolding a Student to Instill Knowledge

Anil Kag · Durmus Alp Emre Acar · Aditya Gangrade · Venkatesh Saligrama

MH1-2-3-4 #61

Keywords: [ large capacity teacher ] [ tiny capacity student ] [ knowledge distillation ] [ budget constrained learning ] [ Deep Learning and representational learning ]


We propose a novel knowledge distillation (KD) method to selectively instill teacher knowledge into a student model motivated by situations where the student's capacity is significantly smaller than that of the teachers. In vanilla KD, the teacher primarily sets a predictive target for the student to follow, and we posit that this target is overly optimistic due to the student's lack of capacity. We develop a novel scaffolding scheme where the teacher, in addition to setting a predictive target, also scaffolds the student's prediction by censoring hard-to-learn examples. Scaffolding utilizes the same information as the teacher's soft-max predictions as inputs, and in this sense, our proposal can be viewed as a natural variant of vanilla KD. We show on synthetic examples that censoring hard-examples leads to smoothening the student's loss landscape so that the student encounters fewer local minima. As a result, it has good generalization properties. Against vanilla KD, we achieve improved performance and are comparable to more intrusive techniques that leverage feature matching on benchmark datasets.

Chat is not available.