REVIEW 2 cited by
VAEs in the Presence of Missing Data
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Real world datasets often contain entries with missing elements e.g. in a medical dataset, a patient is unlikely to have taken all possible diagnostic tests. Variational Autoencoders (VAEs) are popular generative models often used for unsupervised learning. Despite their widespread use it is unclear how best to apply VAEs to datasets with missing data. We develop a novel latent variable model of a corruption process which generates missing data, and derive a corresponding tractable evidence lower bound (ELBO). Our model is straightforward to implement, can handle both missing completely at random (MCAR) and missing not at random (MNAR) data, scales to high dimensional inputs and gives both the VAE encoder and decoder principled access to indicator variables for whether a data element is missing or not. On the MNIST and SVHN datasets we demonstrate improved marginal log-likelihood of observed data and better missing data imputation, compared to existing approaches.
Forward citations
Cited by 2 Pith papers
-
AdaptoNet: Modular Foundation-Adaptive Neural Networks for Cyber-Physical Attack Detection in Power Grids
AdaptoNet, a modular network with a mask-conditioned adaptive module, recovers line-outage detection F1 from below 12% to above 81% under in-region data-denial attacks across four IEEE test systems.
-
Masked Conditioning for Deep Generative Models
Masking conditions during training with varying sparsity schedules lets small VAEs and latent diffusion models generate engineering designs from partially specified inputs.
Discussion (0). Continue with ORCID to comment.