Discovering influential factors in variational autoencoders
作者：
Highlights：
• This paper aims to study variational autoencoder, so as to discover its influential generating factors.
• It shows that the VAE objective inclines to induce mutual information sparsity in factor dimension over the data intrinsic dimension and therefore inclines to result in some non-influential factors whose function on data reconstruction could be 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.
• It show mutual information also influences the lower bound of VAEs reconstruction error and downstream classification task.
摘要
•This paper aims to study variational autoencoder, so as to discover its influential generating factors.•It shows that the VAE objective inclines to induce mutual information sparsity in factor dimension over the data intrinsic dimension and therefore inclines to result in some non-influential factors whose function on data reconstruction could be 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.•It show mutual information also influences the lower bound of VAEs reconstruction error and downstream classification task.
论文关键词：Variational autoencoder,Mutual information,Generative model
论文评审过程：Received 5 May 2019, Revised 16 November 2019, Accepted 14 December 2019, Available online 15 December 2019, Version of Record 20 December 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.107166
