Causal Flow-based Variational Auto-Encoder for Disentangled Causal Representation Learning

arXiv:2304.09010v4 Announce Type: replace
Abstract: Disentangled representation learning aims to learn low-dimensional representations of data, where each dimension corresponds to an underlying generative factor. Currently, Variational Auto-Encoder (VAE) are widely used for disentangled representation learning, with the majority of methods assuming independence among generative factors. However, in real-world scenarios, generative factors typically exhibit complex causal relationships. We thus design a new VAE-based framework named Disentangled Causal Variational Auto-Encoder (DCVAE), which includes a variant of autoregressive flows known as causal flows, …

abstract arxiv auto causal cs.lg data encoder flow generative however learn low representation representation learning stat.me type vae world