Disentangled Representations for Sequence Data using Information Bottleneck Principle

Masanori Yamada, Heecheol Kim, Kosuke Miyoshi, Tomoharu Iwata, Hiroshi Yamakawa

Abstract: We propose the factorizing variational autoencoder (FAVAE), a generative model for learning dis- entangled representations from sequential data via the information bottleneck principle without supe...