Posterior Consistency for Missing Data in Variational Autoencoders
원문 초록
We consider the problem of learning Variational Autoencoders (VAEs), i.e., a type of deep generative model, from data with missing values. Such data is omnipresent in real-world applications of machine learning because complete data is often impossible or too costly to obtain. We particularly focus on improving a VAE's amortized posterior inference, i.e., the encoder, which in the case of missing data can be susceptible to learning inconsistent posterior distributions regarding the missingness. To this end, we provide a formal definition of posterior consistency and propose an approach for regularizing an encoder's posterior distribution which promotes this consistency. We observe that the proposed regularization suggests a different training objective than that typically considered in the literature when facing missing values. Furthermore, we empirically demonstrate that our regularization leads to improved performance in missing value settings in terms of reconstruction quality and downstream tasks utilizing uncertainty in the latent space. This improved performance can be observed for many classes of VAEs including VAEs equipped with normalizing flows.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Leveraging Predictive Equivalence in Decision Trees
Cross-Domain Conditional Diffusion Models for Time Series Imputation
RADAR: Benchmarking Language Models on Imperfect Tabular Data
IMTS is Worth Time $\times$ Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction
Integrative Analysis and Imputation of Multiple Data Streams via Deep Gaussian Processes
ImputeINR: Time Series Imputation via Implicit Neural Representations for Disease Diagnosis with Missing Data
토론
이 논문과 연결된 포럼 글이 아직 없습니다.