Learning conditional variational autoencoders with missing covariates

Siddharth Ramchandran*, Gleb Tikhonov, Otto Lönnroth, Pekka Tiikkainen, Harri Lähdesmäki

*Tämän työn vastaava kirjoittaja

Tutkimustuotos: LehtiartikkeliArticleScientificvertaisarvioitu

34 Lataukset (Pure)

Abstrakti

Conditional variational autoencoders (CVAEs) are versatile deep latent variable models that extend the standard VAE framework by conditioning the generative model with auxiliary covariates. The original CVAE model assumes that the data samples are independent, whereas more recent conditional VAE models, such as the Gaussian process (GP) prior VAEs, can account for complex correlation structures across all data samples. While several methods have been proposed to learn standard VAEs from partially observed datasets, these methods fall short for conditional VAEs. In this work, we propose a method to learn conditional VAEs from datasets in which auxiliary covariates can contain missing values as well. The proposed method augments the conditional VAEs with a prior distribution for the missing covariates and estimates their posterior using amortised variational inference. At training time, our method accounts for the uncertainty associated with the missing covariates while simultaneously maximising the evidence lower bound. We develop computationally efficient methods to learn CVAEs and GP prior VAEs that are compatible with mini-batching. Our experiments on simulated datasets as well as on real-world biomedical datasets show that the proposed method outperforms previous methods in learning conditional VAEs from non-temporal, temporal, and longitudinal datasets.
AlkuperäiskieliEnglanti
Artikkeli110113
JulkaisuPattern Recognition
Vuosikerta147
Varhainen verkossa julkaisun päivämäärä11 marrask. 2023
DOI - pysyväislinkit
TilaJulkaistu - maalisk. 2024
OKM-julkaisutyyppiA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Sormenjälki

Sukella tutkimusaiheisiin 'Learning conditional variational autoencoders with missing covariates'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä