Capturing Label Characteristics in VAEs
We present a principled approach to incorporating labels in VAEs that captures the rich characteristic information associated with those labels. While prior work has typically conflated these by learning latent variables that directly correspond to label values, we argue this is contrary to the intended effect of supervision in VAEs-capturing rich label characteristics with the latents. For example, we may want to capture the characteristics of a face that make it look young, rather than just the age of the person. To this end, we develop the CCVAE, a novel VAE model and concomitant variational objective which captures label characteristics explicitly in the latent space, eschewing direct correspondences between label values and latents. Through judicious structuring of mappings between such characteristic latents and labels, we show that the CCVAE can effectively learn meaningful representations of the characteristics of interest across a variety of supervision schemes. In particular, we show that the CCVAE allows for more effective and more general interventions to be performed, such as smooth traversals within the characteristics for a given label, diverse conditional generation, and transferring characteristics across datapoints.
Code (2)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Game Level Clustering and Generation using Gaussian Mixture VAEs
Variational autoencoders (VAEs) have been shown to be able to generate game levels but require manual exploration of the learned latent space to generate outputs with desired attributes. While conditional VAEs address th…
ClusteringMixture-of-experts VAEs can disregard variation in surjective multimodal data
Machine learning systems are often deployed in domains that entail data from multiple modalities, for example, phenotypic and genotypic characteristics describe patients in healthcare. Previous works have developed multi…
Mixture-of-ExpertsSpatial Variational Auto-Encoding via Matrix-Variate Normal Distributions
The key idea of variational auto-encoders (VAEs) resembles that of traditional auto-encoder models in which spatial information is supposed to be explicitly encoded in the latent space. However, the latent variables in V…
ShaLa: Multimodal Shared Latent Space Modelling
This paper presents a novel generative framework for learning shared latent representations across multimodal data. Many advanced multimodal methods focus on capturing all combinations of modality-specific details across…
Handling Incomplete Heterogeneous Data using VAEs
Variational autoencoders (VAEs), as well as other generative models, have been shown to be efficient and accurate for capturing the latent structure of vast amounts of complex high-dimensional data. However, existing VAE…
Imputation