PrUE: Distilling Knowledge from Sparse Teacher Networks

TL;DR

PrUE is a pruning technique that simplifies teacher networks by enlarging their prediction uncertainty, leading to improved knowledge distillation and better student network performance across multiple datasets.

Contribution

This paper introduces PrUE, a novel pruning method that reduces teacher certainty to generate softer labels, enhancing knowledge transfer in model compression.

Findings

Students trained with sparse teachers outperform those with full teachers.

PrUE enables distillation from deeper networks, improving student accuracy.

Method shows consistent gains on CIFAR-10/100, Tiny-ImageNet, and ImageNet.

Abstract

Although deep neural networks have enjoyed remarkable success across a wide variety of tasks, their ever-increasing size also imposes significant overhead on deployment. To compress these models, knowledge distillation was proposed to transfer knowledge from a cumbersome (teacher) network into a lightweight (student) network. However, guidance from a teacher does not always improve the generalization of students, especially when the size gap between student and teacher is large. Previous works argued that it was due to the high certainty of the teacher, resulting in harder labels that were difficult to fit. To soften these labels, we present a pruning method termed Prediction Uncertainty Enlargement (PrUE) to simplify the teacher. Specifically, our method aims to decrease the teacher's certainty about data, thereby generating soft predictions for students. We empirically investigate the effectiveness of the proposed method with experiments on CIFAR-10/100, Tiny-ImageNet, and ImageNet. Results indicate that student networks trained with sparse teachers achieve better performance. Besides, our method allows researchers to distill knowledge from deeper networks to improve students further. Our code is made public at: \url{https://github.com/wangshaopu/prue}.