MLLGJul 14, 2020

Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks

arXiv:2007.07124v433 citations
AI Analysis

It addresses a gap in understanding how VAE training issues affect practical applications, but is incremental in nature.

The paper characterizes conditions under which VAE training exhibits pathologies and links these failure modes to negative impacts on downstream tasks like representation learning and adversarial robustness.

Variational Auto-encoders (VAEs) are deep generative latent variable models that are widely used for a number of downstream tasks. While it has been demonstrated that VAE training can suffer from a number of pathologies, existing literature lacks characterizations of exactly when these pathologies occur and how they impact downstream task performance. In this paper, we concretely characterize conditions under which VAE training exhibits pathologies and connect these failure modes to undesirable effects on specific downstream tasks, such as learning compressed and disentangled representations, adversarial robustness, and semi-supervised learning.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes