# Continual Learning with Invertible Generative Models

arXiv: https://arxiv.org/abs/2202.05694 · HTML: https://mlsanity.com/paper/2202.05694/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 50 references that are in the map.
- First posted on arXiv 11 Feb 2022.

## Builds on (most cited first, 30 of 30)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Normalizing Flows for Probabilistic Modeling and Inference](https://mlsanity.com/paper/1912.02762/) (2019)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Improving Variational Inference with Inverse Autoregressive Flow](https://mlsanity.com/paper/1606.04934/) (2016)
- [Class-incremental learning: survey and performance evaluation on image classification](https://mlsanity.com/paper/2010.15277/) (2020)
- [Supermasks in Superposition](https://mlsanity.com/paper/2006.14769/) (2020)
- [Task-Free Continual Learning](https://mlsanity.com/paper/1812.03596/) (2018)
- [Learning Likelihoods with Conditional Normalizing Flows](https://mlsanity.com/paper/1912.00042/) (2019)
- [Continual Unsupervised Representation Learning](https://mlsanity.com/paper/1910.14481/) (2019)
- [Adversarial Continual Learning](https://mlsanity.com/paper/2003.09553/) (2020)
- [InfoVAE: Information Maximizing Variational Autoencoders](https://mlsanity.com/paper/1706.02262/) (2017)
- [Continuous Learning in Single-Incremental-Task Scenarios](https://mlsanity.com/paper/1806.08568/) (2018)
- [Generative Feature Replay For Class-Incremental Learning](https://mlsanity.com/paper/2004.09199/) (2020)
- [Towards Deeper Understanding of Variational Autoencoding Models](https://mlsanity.com/paper/1702.08658/) (2017)
- [Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates](https://mlsanity.com/paper/2010.00373/) (2020)
- [Efficient Continual Learning in Neural Networks with Embedding Regularization](https://mlsanity.com/paper/1909.03742/) (2019)
- [Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis](https://mlsanity.com/paper/1903.11250/) (2019)
- [Structured Ensembles: an Approach to Reduce the Memory Footprint of Ensemble Methods](https://mlsanity.com/paper/2105.02551/) (2021)

## Built on by (most cited first, 3 of 3)

- [Overcoming Catastrophic Forgetting in Tabular Data Classification: A Pseudorehearsal-based approach](https://mlsanity.com/paper/2407.09039/) (2024)
- [Improvements of Dark Experience Replay and Reservoir Sampling towards Better Balance between Consolidation and Plasticity](https://mlsanity.com/paper/2504.20932/) (2025)
- [Class incremental learning with probability dampening and cascaded gated classifier](https://mlsanity.com/paper/2402.01262/) (2024)

## Abstract (arXiv)

Catastrophic forgetting (CF) happens whenever a neural network overwrites past knowledge while being trained on new tasks. Common techniques to handle CF include regularization of the weights (using, e.g., their importance on past tasks), and rehearsal strategies, where the network is constantly re-trained on past data. Generative models have also been applied for the latter, in order to have endless sources of data. In this paper, we propose a novel method that combines the strengths of regularization and generative-based rehearsal approaches. Our generative model consists of a normalizing flow (NF), a probabilistic and invertible neural network, trained on the internal embeddings of the network. By keeping a single NF throughout the training process, we show that our memory overhead remains constant. In addition, exploiting the invertibility of the NF, we propose a simple approach to regularize the network's embeddings with respect to past tasks. We show that our method performs favorably with respect to state-of-the-art approaches in the literature, with bounded computational power and memory overheads.