Teacher-Student Compression with Generative Adversarial Networks

More accurate machine learning models often demand more computation and memory at test time, making them difficult to deploy on CPU- or memory-constrained devices. Teacher-student compression (TSC), also known as distillation, alleviates this burden by training a less expensive student model to mimi...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-03
Main Authors: Liu, Ruishan, Fusi, Nicolo, Mackey, Lester
Format: Article
Language:English
Subjects:
Compression tests
Computer memory
Data compression
Datasets
Distillation
Generative adversarial networks
Image classification
Machine learning
Memory devices
Model accuracy
Neural networks
Teachers
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:More accurate machine learning models often demand more computation and memory at test time, making them difficult to deploy on CPU- or memory-constrained devices. Teacher-student compression (TSC), also known as distillation, alleviates this burden by training a less expensive student model to mimic the expensive teacher model while maintaining most of the original accuracy. However, when fresh data is unavailable for the compression task, the teacher's training data is typically reused, leading to suboptimal compression. In this work, we propose to augment the compression dataset with synthetic data from a generative adversarial network (GAN) designed to approximate the training data distribution. Our GAN-assisted TSC (GAN-TSC) significantly improves student accuracy for expensive models such as large random forests and deep neural networks on both tabular and image datasets. Building on these results, we propose a comprehensive metric---the TSC Score---to evaluate the quality of synthetic datasets based on their induced TSC performance. The TSC Score captures both data diversity and class affinity, and we illustrate its benefits over the popular Inception Score in the context of image classification.
ISSN:2331-8422