Knowledge Consistency between Neural Networks and Beyond
Abstract
This paper aims to analyze knowledge consistency between pre-trained deep neural networks. We propose a generic definition for knowledge consistency between neural networks at different fuzziness levels. A task-agnostic method is designed to disentangle feature components, which represent the consistent knowledge, from raw intermediate-layer features of each neural network. As a generic tool, our method can be broadly used for different applications. In preliminary experiments, we have used knowledge consistency as a tool to diagnose representations of neural networks. Knowledge consistency provides new insights to explain the success of existing deep-learning techniques, such as knowledge distillation and network compression. More crucially, knowledge consistency can also be used to refine pre-trained networks and boost performance.
Cite
@article{arxiv.1908.01581,
title = {Knowledge Consistency between Neural Networks and Beyond},
author = {Ruofan Liang and Tianlin Li and Longfei Li and Jing Wang and Quanshi Zhang},
journal= {arXiv preprint arXiv:1908.01581},
year = {2020}
}