LGAINov 30, 2020

A Selective Survey on Versatile Knowledge Distillation Paradigm for Neural Network Models

arXiv:2011.14554v13 citations
AI Analysis

This survey provides an overview of knowledge distillation for researchers and practitioners to develop optimized deep neural network models.

This paper surveys knowledge distillation (KD) frameworks, initially a model compression technique, now with versatile applications. It reviews KD's characteristics based on three ingredients: distilled knowledge/loss, teacher-student paradigm, and distillation process, and explores its direct and combined applications.

This paper aims to provide a selective survey about knowledge distillation(KD) framework for researchers and practitioners to take advantage of it for developing new optimized models in the deep neural network field. To this end, we give a brief overview of knowledge distillation and some related works including learning using privileged information(LUPI) and generalized distillation(GD). Even though knowledge distillation based on the teacher-student architecture was initially devised as a model compression technique, it has found versatile applications over various frameworks. In this paper, we review the characteristics of knowledge distillation from the hypothesis that the three important ingredients of knowledge distillation are distilled knowledge and loss,teacher-student paradigm, and the distillation process. In addition, we survey the versatility of the knowledge distillation by studying its direct applications and its usage in combination with other deep learning paradigms. Finally we present some future works in knowledge distillation including explainable knowledge distillation where the analytical analysis of the performance gain is studied and the self-supervised learning which is a hot research topic in deep learning community.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes