Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Shiqi, Liu, Jingxin, Zhao, Qian, Cao, Xiangyong, Li, Huibin, Meng, Deyu, Meng, Hongying, Liu, Sheng
Format: Preprint
Publié: 2018
Sujets:
Accès en ligne:https://arxiv.org/abs/1809.01804
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908700408545280
author Liu, Shiqi
Liu, Jingxin
Zhao, Qian
Cao, Xiangyong
Li, Huibin
Meng, Deyu
Meng, Hongying
Liu, Sheng
author_facet Liu, Shiqi
Liu, Jingxin
Zhao, Qian
Cao, Xiangyong
Li, Huibin
Meng, Deyu
Meng, Hongying
Liu, Sheng
contents In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downstream tasks. In this work, we focus on supervising the influential factors extracted by the variational autoencoder(VAE). The VAE is proposed to learn independent low dimension representation while facing the problem that sometimes pre-set factors are ignored. We argue that the mutual information of the input and each learned factor of the representation plays a necessary indicator of discovering the influential factors. We find the VAE objective inclines to induce mutual information sparsity in factor dimension over the data intrinsic dimension and therefore result in some non-influential factors whose function on data reconstruction could be ignored. We show mutual information also influences the lower bound of the VAE's reconstruction error and downstream classification task. To make such indicator applicable, we design an algorithm for calculating the mutual information for the VAE and prove its consistency. Experimental results on MNIST, CelebA and DEAP datasets show that mutual information can help determine influential factors, of which some are interpretable and can be used to further generation and classification tasks, and help discover the variant that connects with emotion on DEAP dataset.
format Preprint
id arxiv_https___arxiv_org_abs_1809_01804
institution arXiv
publishDate 2018
record_format arxiv
spellingShingle Discovering Influential Factors in Variational Autoencoders
Liu, Shiqi
Liu, Jingxin
Zhao, Qian
Cao, Xiangyong
Li, Huibin
Meng, Deyu
Meng, Hongying
Liu, Sheng
Machine Learning
In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downstream tasks. In this work, we focus on supervising the influential factors extracted by the variational autoencoder(VAE). The VAE is proposed to learn independent low dimension representation while facing the problem that sometimes pre-set factors are ignored. We argue that the mutual information of the input and each learned factor of the representation plays a necessary indicator of discovering the influential factors. We find the VAE objective inclines to induce mutual information sparsity in factor dimension over the data intrinsic dimension and therefore result in some non-influential factors whose function on data reconstruction could be ignored. We show mutual information also influences the lower bound of the VAE's reconstruction error and downstream classification task. To make such indicator applicable, we design an algorithm for calculating the mutual information for the VAE and prove its consistency. Experimental results on MNIST, CelebA and DEAP datasets show that mutual information can help determine influential factors, of which some are interpretable and can be used to further generation and classification tasks, and help discover the variant that connects with emotion on DEAP dataset.
title Discovering Influential Factors in Variational Autoencoders
topic Machine Learning
url https://arxiv.org/abs/1809.01804