Learning Representation from Neural Fisher Kernel with Low-rank Approximation
Ruixiang ZHANG, Shuangfei Zhai, Etai Littwin, Joshua M. Susskind
Abstract
In this paper, we study the representation of neural networks from the view of kernels. We first define the Neural Fisher Kernel (NFK), which is the Fisher Kernel applied to neural networks. We show that NFK can be computed for both supervised and unsupervised learning models, which can serve as a unified tool for representation extraction. Furthermore, we show that practical NFKs exhibit low-rank structures. We then propose an efficient algorithm that computes a low-rank approximation of NFK, which scales to large datasets and networks. We show that the low-rank approximation of NFKs derived from unsupervised generative models and supervised learning models gives rise to high-quality compact representations of data, achieving competitive results on a variety of machine learning tasks.
BibTeX
@inproceedings{
zhang2022learning,
title={Learning Representation from Neural Fisher Kernel with Low-rank Approximation},
author={Ruixiang ZHANG and Shuangfei Zhai and Etai Littwin and Joshua M. Susskind},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=J1rhANsCY9}
}