# Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks

arXiv: https://arxiv.org/abs/2007.07124 · HTML: https://mlsanity.com/paper/2007.07124/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jul 2020.

## Built on by (most cited first, 16 of 16)

- [Identifiability of deep generative models without auxiliary information](https://mlsanity.com/paper/2206.10044/) (2022)
- [ARTxAI: Explainable Artificial Intelligence Curates Deep Representation Learning for Artistic Images using Fuzzy Techniques](https://mlsanity.com/paper/2308.15284/) (2023)
- [HyperSINDy: Deep Generative Modeling of Nonlinear Stochastic Governing Equations](https://mlsanity.com/paper/2310.04832/) (2023)
- [The Deep Generative Decoder: MAP estimation of representations improves modeling of single-cell RNA data](https://mlsanity.com/paper/2110.06672/) (2021)
- [Towards a Taxonomy for the Use of Synthetic Data in Advanced Analytics](https://mlsanity.com/paper/2212.02622/) (2022)
- [A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation](https://mlsanity.com/paper/2402.18402/) (2024)
- [Data-driven Seasonal Climate Predictions via Variational Inference and Transformers](https://mlsanity.com/paper/2503.20466/) (2025)
- [Challenging the Semi-Supervised VAE Framework for Text Classification](https://mlsanity.com/paper/2109.12969/) (2021)
- [Interpretable Sentence Representation with Variational Autoencoders and Attention](https://mlsanity.com/paper/2305.02810/) (2023)
- [Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders](https://mlsanity.com/paper/2403.08941/) (2024)
- [Survey of Deep Learning and Physics-Based Approaches in Computational Wave Imaging](https://mlsanity.com/paper/2410.08329/) (2024)
- [PH-VAE: A Polynomial Hierarchical Variational Autoencoder Towards Disentangled Representation Learning](https://mlsanity.com/paper/2502.02856/) (2025)
- [Uncovering Physical Drivers of Dark Matter Halo Structures with Auxiliary-Variable-Guided Generative Models](https://mlsanity.com/paper/2602.23518/) (2026)
- [eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions](https://mlsanity.com/paper/2607.01275/) (2026)
- [Neural Operator-enabled Topology-informed Evolutionary Strategy for PDE-Constrained Optimization](https://mlsanity.com/paper/2607.07682/) (2026)
- [Latent Similarity Gaussian Processes: A Theory-Grounded Approach to Personalized Suicide-Risk Forecasting for Clinical Decision-Support](https://mlsanity.com/paper/2610.06355/) (2026)

## Abstract (arXiv)

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.