# InfoVAE: Information Maximizing Variational Autoencoders

arXiv: https://arxiv.org/abs/1706.02262 · HTML: https://mlsanity.com/paper/1706.02262/

## Key facts

- Cited by 124 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2017.

## Built on by (most cited first, 30 of 124)

- [Diffusion-based Generation, Optimization, and Planning in 3D Scenes](https://mlsanity.com/paper/2301.06015/) (2023)
- [D2C: Diffusion-Denoising Models for Few-shot Conditional Generation](https://mlsanity.com/paper/2106.06819/) (2021)
- [HDMI: High-order Deep Multiplex Infomax](https://mlsanity.com/paper/2102.07810/) (2021)
- [To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review](https://mlsanity.com/paper/2304.09355/) (2023)
- [InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models](https://mlsanity.com/paper/2306.08757/) (2023)
- [Stochastic Image-to-Video Synthesis using cINNs](https://mlsanity.com/paper/2105.04551/) (2021)
- [Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learning](https://mlsanity.com/paper/2303.16535/) (2023)
- [Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review](https://mlsanity.com/paper/2307.13125/) (2023)
- [iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis](https://mlsanity.com/paper/2107.02790/) (2021)
- [Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking](https://mlsanity.com/paper/2102.09117/) (2021)
- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification](https://mlsanity.com/paper/2303.10610/) (2023)
- [Latent Feature-Guided Diffusion Models for Shadow Removal](https://mlsanity.com/paper/2312.02156/) (2023)
- [Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement](https://mlsanity.com/paper/2402.09712/) (2024)
- [Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Case](https://mlsanity.com/paper/2206.08309/) (2022)
- [Fairness without the sensitive attribute via Causal Variational Autoencoder](https://mlsanity.com/paper/2109.04999/) (2021)
- [A Differential Entropy Estimator for Training Neural Networks](https://mlsanity.com/paper/2202.06618/) (2022)
- [Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance](https://mlsanity.com/paper/2509.02055/) (2025)
- [Exploring Autoencoder-based Error-bounded Compression for Scientific Data](https://mlsanity.com/paper/2105.11730/) (2021)
- [Lifting Architectural Constraints of Injective Flows](https://mlsanity.com/paper/2306.01843/) (2023)
- [Deep Generative Models for Detector Signature Simulation: A Taxonomic Review](https://mlsanity.com/paper/2312.09597/) (2023)
- [Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction](https://mlsanity.com/paper/2111.06636/) (2021)
- [Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directions](https://mlsanity.com/paper/2303.12484/) (2023)
- [Population Aware Diffusion for Time Series Generation](https://mlsanity.com/paper/2501.00910/) (2025)
- [Group Equivariant Subsampling](https://mlsanity.com/paper/2106.05886/) (2021)
- [Interpretable Molecular Graph Generation via Monotonic Constraints](https://mlsanity.com/paper/2203.00412/) (2022)
- [Behavior-Driven Synthesis of Human Dynamics](https://mlsanity.com/paper/2103.04677/) (2021)
- [Hierarchical Latent Structure for Multi-Modal Vehicle Trajectory Forecasting](https://mlsanity.com/paper/2207.04624/) (2022)
- [GraspLDM: Generative 6-DoF Grasp Synthesis using Latent Diffusion Models](https://mlsanity.com/paper/2312.11243/) (2023)
- [Disentangled Spatiotemporal Graph Generative Models](https://mlsanity.com/paper/2203.00411/) (2022)

## Abstract (arXiv)

A key advance in learning generative models is the use of amortized inference distributions that are jointly trained with the models. We find that existing training objectives for variational autoencoders can lead to inaccurate amortized inference distributions and, in some cases, improving the objective provably degrades the inference quality. In addition, it has been observed that variational autoencoders tend to ignore the latent variables when combined with a decoding distribution that is too flexible. We again identify the cause in existing training criteria and propose a new class of objectives (InfoVAE) that mitigate these problems. We show that our model can significantly improve the quality of the variational posterior and can make effective use of the latent features regardless of the flexibility of the decoding distribution. Through extensive qualitative and quantitative analyses, we demonstrate that our models outperform competing approaches on multiple performance metrics.