Understanding VAEs in Fisher-Shannon Plane

Association for the Advancement of Artificial Intelligence
Publication Type:
Conference Proceeding
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019, 33 (1), pp. 5917 - 5924
Issue Date:
Filename Description Size
Understanding VAEs in Fisher-Shannon Plane.pdfPublished version5.62 MB
Adobe PDF
Full metadata record
In information theory, Fisher information and Shannon information (entropy) are respectively used to quantify the uncertainty associated with the distribution modeling and the uncertainty in specifying the outcome of given variables. These two quantities are complementary and are jointly applied to information behavior analysis in most cases. The uncertainty property in information asserts a fundamental trade-off between Fisher information and Shannon information, which enlightens us the relationship between the encoder and the decoder in variational auto-encoders (VAEs). In this paper, we investigate VAEs in the Fisher-Shannon plane, and demonstrate that the representation learning and the log-likelihood estimation are intrinsically related to these two information quantities. Through extensive qualitative and quantitative experiments, we provide with a better comprehension of VAEs in tasks such as high-resolution reconstruction, and representation learning in the perspective of Fisher information and Shannon information. We further propose a variant of VAEs, termed as Fisher auto-encoder (FAE), for practical needs to balance Fisher information and Shannon information. Our experimental results have demonstrated its promise in improving the reconstruction accuracy and avoiding the noninformative latent code as occurred in previous works.
Please use this identifier to cite or link to this item: