# Unsupervised Continual Learning with Growing Self-Organizing Maps and Synthetic Replay

arXiv: https://arxiv.org/abs/2608.27662 · HTML: https://mlsanity.com/paper/2608.27662/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [Progress & Compress: A scalable framework for continual learning](https://mlsanity.com/paper/1805.06370/) (2018)
- [Task-Free Continual Learning](https://mlsanity.com/paper/1812.03596/) (2018)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning](https://mlsanity.com/paper/2205.13218/) (2022)
- [Continual Unsupervised Representation Learning](https://mlsanity.com/paper/1910.14481/) (2019)
- [Continual Prototype Evolution: Learning Online from Non-Stationary Data Streams](https://mlsanity.com/paper/2009.00919/) (2020)
- [A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning](https://mlsanity.com/paper/2001.00689/) (2020)
- [Gradient-based Editing of Memory Examples for Online Task-free Continual Learning](https://mlsanity.com/paper/2006.15294/) (2020)
- [Recent Advances of Foundation Language Models-based Continual Learning: A Survey](https://mlsanity.com/paper/2405.18653/) (2024)
- [Task-Free Continual Learning via Online Discrepancy Distance Learning](https://mlsanity.com/paper/2210.06579/) (2022)
- [An Adaptive Random Path Selection Approach for Incremental Learning](https://mlsanity.com/paper/1906.01120/) (2019)
- [Gradient Episodic Memory with a Soft Constraint for Continual Learning](https://mlsanity.com/paper/2011.07801/) (2020)
- [Continual Variational Autoencoder Learning via Online Cooperative Memorization](https://mlsanity.com/paper/2207.10131/) (2022)
- [Continual Learning with Self-Organizing Maps](https://mlsanity.com/paper/1904.09330/) (2019)
- [Continual Competitive Memory: A Neural System for Online Task-Free Lifelong Learning](https://mlsanity.com/paper/2106.13300/) (2021)
- [Dendritic Self-Organizing Maps for Continual Learning](https://mlsanity.com/paper/2110.13611/) (2021)
- [Reducing Catastrophic Forgetting in Self Organizing Maps with Internally-Induced Generative Replay](https://mlsanity.com/paper/2112.04728/) (2021)
- [Exemplar-free Class Incremental Learning via Discriminative and Comparable One-class Classifiers](https://mlsanity.com/paper/2201.01488/) (2022)

## Abstract (arXiv)

This work presents a generative continual learning framework based on growing self-organizing maps (GSOMs) that are augmented with learned distributional statistics as well as encoder-decoder models for class-incremental learning. The proposed approach enables exemplar-free replay using distributional statistical memory, which eliminates the need to store raw data. Each GSOM unit maintains its own mean, variance, and covariance estimates, which are subsequently used to generate synthetic samples for replay; in encoder-decoder configurations, these samples are then decoded back into the input space (via ancestral sampling) for subsequent training. Our method is fully unsupervised, as it does not rely on explicit task boundaries or class labels during training. Results across multiple benchmarks show that the proposed approach achieves performance competitive even with supervised state-of-the-art memory-based methods while consistently outperforming memory-free approaches. In several settings, our framework matches or exceeds existing baselines, particularly in challenging single-class incremental scenarios. We also provide baseline results for single-class incremental TinyImageNet and MiniImageNet, offering a useful reference for future work. This work highlights the effectiveness of an unsupervised, adaptive, topology-driven neural form of statistical replay as a scalable, flexible approach to continual learning.