Class Incremental Continual Learning with Self-Organizing Maps and Synthetic Replay
cs.LG
Submitted: 2025-08-28
Updated: 2026-08-27
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: This work introduces a novel generative continual learning framework based on self-organizing maps (SOMs), a brain-inspired natural computing model, extended with learned distributional statistics
Terminology
Abstract
This work introduces a novel generative continual learning framework based on self-organizing maps (SOMs), a brain-inspired natural computing model, extended with learned distributional statistics and encoder--decoder models for class incremental continual learning. These extended SOMs enable exemplar-free replay with fixed-capacity statistical memory, eliminating the need to store raw data samples. For high-dimensional input spaces, the SOM operates over the latent space of the encoder--decoder, while for lower-dimensional inputs, the SOM operates in a standalone fashion. Our method stores a running mean, variance, and covariance for each SOM unit, from which synthetic samples are then generated during future learning iterations. For the encoder--decoder method, generated samples are fed through the decoder to be used in subsequent replay. Experimental results on standard class-incremental benchmarks show that our approach performs competitively with state-of-the-art memory-based methods and outperforms memory-free methods, notably improving over the best state-of-the-art single-class incremental performance without pretrained encoders on CIFAR-10 and CIFAR-100 by nearly 10% and 7%, respectively. We also achieve the best performance on single-class incremental CIFAR-100 using a foundational encoder-decoder and present the first baseline results for single-class incremental TinyImageNet. Our methodology facilitates easy visualization of the learning process and can also be utilized as a generative model post-training. Overall, the results demonstrate that SOM-based statistical replay offers a scalable, label-free, exemplar-free approach to class-incremental continual learning under standard task-boundary protocols.
Sources
- Online Continual Learning with Maximally Interfered Retrieval
- Gradient based sample selection for online continual learning
- VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
- Continual Learning with Self-Organizing Maps
- Dark Experience for General Continual Learning: a Strong, Simple Baseline
- New Insights on Reducing Abrupt Representation Change in Online Continual Learning
- Efficient Lifelong Learning with A-GEM
- CLA: Latent Alignment for Online Continual Self-Supervised Learning
- Auto-Encoding Variational Bayes
- Learning without Forgetting
- Gradient Episodic Memory for Continual Learning
- Representational Continuity for Unsupervised Continual Learning
- Continual Competitive Memory: A Neural System for Online Task-Free Lifelong Learning
- Dendritic Self-Organizing Maps for Continual Learning
- iCaRL: Incremental Classifier and Representation Learning
- Tree-CNN: A Hierarchical Deep Convolutional Neural Network for Incremental Learning
- Progressive Neural Networks
- Progress & Compress: A scalable framework for continual learning
- Continual Learning with Deep Generative Replay
- Very Deep Convolutional Networks for Large-Scale Image Recognition
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks