# BooVAE: Boosting Approach for Continual Learning of VAE

arXiv: https://arxiv.org/abs/1908.11853 · HTML: https://mlsanity.com/paper/1908.11853/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Aug 2019.

## Built on by (most cited first, 18 of 18)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition](https://mlsanity.com/paper/2207.07730/) (2022)
- [Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy](https://mlsanity.com/paper/2312.10549/) (2023)
- [Exploring Continual Learning of Diffusion Models](https://mlsanity.com/paper/2303.15342/) (2023)
- [Continual Variational Autoencoder Learning via Online Cooperative Memorization](https://mlsanity.com/paper/2207.10131/) (2022)
- [Hierarchical VAE with a Diffusion-based VampPrior](https://mlsanity.com/paper/2412.01373/) (2024)
- [Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning](https://mlsanity.com/paper/2106.12196/) (2021)
- [Scaling Image Tokenizers with Grouped Spherical Quantization](https://mlsanity.com/paper/2412.02632/) (2024)
- [An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning](https://mlsanity.com/paper/2211.16780/) (2022)
- [Lifelong Learning of Video Diffusion Models From a Single Video Stream](https://mlsanity.com/paper/2406.04814/) (2024)
- [Information-Theoretic Dual Memory System for Continual Learning](https://mlsanity.com/paper/2501.07382/) (2025)
- [The Bayesian Approach to Continual Learning: An Overview](https://mlsanity.com/paper/2507.08922/) (2025)
- [Bayesian Flow Networks in Continual Learning](https://mlsanity.com/paper/2310.12001/) (2023)
- [Adapt & Align: Continual Learning with Generative Models Latent Space Alignment](https://mlsanity.com/paper/2312.13699/) (2023)
- [C2INet: Realizing Incremental Trajectory Prediction with Prior-Aware Continual Causal Intervention](https://mlsanity.com/paper/2411.12313/) (2024)
- [Deep evolving semi-supervised anomaly detection](https://mlsanity.com/paper/2412.00860/) (2024)
- [Continual learning via probabilistic exchangeable sequence modelling](https://mlsanity.com/paper/2503.20725/) (2025)
- [Continual Learning for non-stationary regression via Memory-Efficient Replay](https://mlsanity.com/paper/2602.09720/) (2026)

## Abstract (arXiv)

Variational autoencoder (VAE) is a deep generative model for unsupervised learning, allowing to encode observations into the meaningful latent space. VAE is prone to catastrophic forgetting when tasks arrive sequentially, and only the data for the current one is available. We address this problem of continual learning for VAEs. It is known that the choice of the prior distribution over the latent space is crucial for VAE in the non-continual setting. We argue that it can also be helpful to avoid catastrophic forgetting. We learn the approximation of the aggregated posterior as a prior for each task. This approximation is parametrised as an additive mixture of distributions induced by encoder evaluated at trainable pseudo-inputs. We use a greedy boosting-like approach with entropy regularisation to learn the components. This method encourages components diversity, which is essential as we aim at memorising the current task with the fewest components possible. Based on the learnable prior, we introduce an end-to-end approach for continual learning of VAEs and provide empirical studies on commonly used benchmarks (MNIST, Fashion MNIST, NotMNIST) and CelebA datasets. For each dataset, the proposed method avoids catastrophic forgetting in a fully automatic way.