# Prototype-Guided Memory Replay for Continual Learning

arXiv: https://arxiv.org/abs/2108.12641 · HTML: https://mlsanity.com/paper/2108.12641/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 57 references that are in the map.
- First posted on arXiv 28 Aug 2021.

## Builds on (most cited first, 30 of 40)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [An Empirical Study of Example Forgetting during Deep Neural Network Learning](https://mlsanity.com/paper/1812.05159/) (2018)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Variational Continual Learning](https://mlsanity.com/paper/1710.10628/) (2017)
- [Task-Free Continual Learning](https://mlsanity.com/paper/1812.03596/) (2018)
- [Meta-Learning Representations for Continual Learning](https://mlsanity.com/paper/1905.12588/) (2019)
- [Episodic Memory in Lifelong Language Learning](https://mlsanity.com/paper/1906.01076/) (2019)
- [FearNet: Brain-Inspired Model for Incremental Learning](https://mlsanity.com/paper/1711.10563/) (2017)
- [LAMOL: LAnguage MOdeling for Lifelong Language Learning](https://mlsanity.com/paper/1909.03329/) (2019)
- [Uncertainty-based Continual Learning with Adaptive Regularization](https://mlsanity.com/paper/1905.11614/) (2019)
- [A continual learning survey: Defying forgetting in classification tasks](https://mlsanity.com/paper/1909.08383/) (2019)
- [Overcoming Catastrophic Forgetting with Unlabeled Data in the Wild](https://mlsanity.com/paper/1903.12648/) (2019)
- [Continual Learning for Text Classification with Information Disentanglement Based Regularization](https://mlsanity.com/paper/2104.05489/) (2021)
- [Learning to Continually Learn](https://mlsanity.com/paper/2002.09571/) (2020)
- [Sentence Embedding Alignment for Lifelong Relation Extraction](https://mlsanity.com/paper/1903.02588/) (2019)
- [Compositional Generalization for Primitive Substitutions](https://mlsanity.com/paper/1910.02612/) (2019)

## Built on by (most cited first, 19 of 19)

- [Recent Advances of Multimodal Continual Learning: A Comprehensive Survey](https://mlsanity.com/paper/2410.05352/) (2024)
- [Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning](https://mlsanity.com/paper/2308.02346/) (2023)
- [ProtoDepth: Unsupervised Continual Depth Completion with Prototypes](https://mlsanity.com/paper/2503.12745/) (2025)
- [Self-paced Weight Consolidation for Continual Learning](https://mlsanity.com/paper/2307.10845/) (2023)
- [Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modelling](https://mlsanity.com/paper/2407.15429/) (2024)
- [Vision-Language Navigation with Continual Learning](https://mlsanity.com/paper/2409.02561/) (2024)
- [Learning to Learn for Few-shot Continual Active Learning](https://mlsanity.com/paper/2311.03732/) (2023)
- [AdaptCL: Adaptive Continual Learning for Tackling Heterogeneity in Sequential Datasets](https://mlsanity.com/paper/2207.11005/) (2022)
- [Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning](https://mlsanity.com/paper/2403.18266/) (2024)
- [HPCR: Holistic Proxy-based Contrastive Replay for Online Continual Learning](https://mlsanity.com/paper/2309.15038/) (2023)
- [Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning](https://mlsanity.com/paper/2311.15161/) (2023)
- [Constructing Enhanced Mutual Information for Online Class-Incremental Learning](https://mlsanity.com/paper/2407.18526/) (2024)
- [LSEBMCL: A Latent Space Energy-Based Model for Continual Learning](https://mlsanity.com/paper/2501.05495/) (2025)
- [Flashbacks to Harmonize Stability and Plasticity in Continual Learning](https://mlsanity.com/paper/2506.00477/) (2025)
- [Natural Mitigation of Catastrophic Interference: Continual Learning in Power-Law Learning Environments](https://mlsanity.com/paper/2401.10393/) (2024)
- [ProDER: A Continual Learning Approach for Fault Classification and Localization in Evolving Smart Grids](https://mlsanity.com/paper/2511.05420/) (2025)
- [PPSEBM: An Energy-Based Model with Progressive Parameter Selection for Continual Learning](https://mlsanity.com/paper/2512.15658/) (2025)
- [PKI: Prior Knowledge-Infused Neural Network for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2601.08493/) (2026)
- [Memory-efficient Continual Learning with Prototypical Exemplar Condensation](https://mlsanity.com/paper/2603.13804/) (2026)

## Abstract (arXiv)

Continual learning (CL) refers to a machine learning paradigm that learns continuously without forgetting previously acquired knowledge. Thereby, major difficulty in CL is catastrophic forgetting of preceding tasks, caused by shifts in data distributions. Existing CL models often save a large number of old examples and stochastically revisit previously seen data to retain old knowledge. However, the occupied memory size keeps enlarging along with accumulating seen data. Hereby, we propose a memory-efficient CL method by storing a few samples to achieve good performance. We devise a dynamic prototype-guided memory replay module and incorporate it into an online meta-learning model. We conduct extensive experiments on text classification and investigate the effect of training set orders on CL model performance. The experimental results testify the superiority of our method in terms of forgetting mitigation and efficiency.