# Dynamic Prototype Rehearsal for Continual ECG Arrhythmia Detection

arXiv: https://arxiv.org/abs/2501.07555 · HTML: https://mlsanity.com/paper/2501.07555/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 13 Jan 2025.

## Builds on (most cited first, 15 of 15)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [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)
- [Rainbow Memory: Continual Learning with a Memory of Diverse Samples](https://mlsanity.com/paper/2103.17230/) (2021)
- [GAN Memory with No Forgetting](https://mlsanity.com/paper/2006.07543/) (2020)
- [Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning](https://mlsanity.com/paper/2110.04593/) (2021)
- [Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer](https://mlsanity.com/paper/2211.00789/) (2022)
- [Reproducibility Report: La-MAML: Look-ahead Meta Learning for Continual Learning](https://mlsanity.com/paper/2102.05824/) (2021)
- [Continual Learning via Sequential Function-Space Variational Inference](https://mlsanity.com/paper/2312.17210/) (2023)
- [Continual Learning on Noisy Data Streams via Self-Purified Replay](https://mlsanity.com/paper/2110.07735/) (2021)
- [Which Samples Should be Learned First: Easy or Hard?](https://mlsanity.com/paper/2110.05481/) (2021)
- [Analysis of Augmentations for Contrastive ECG Representation Learning](https://mlsanity.com/paper/2206.07656/) (2022)
- [In-Distribution and Out-of-Distribution Self-supervised ECG Representation Learning for Arrhythmia Detection](https://mlsanity.com/paper/2304.06427/) (2023)

## Built on by (most cited first, 4 of 4)

- [Investigating ECG Diagnosis with Ambiguous Labels using Partial Label Learning](https://mlsanity.com/paper/2512.11095/) (2025)
- [SPOTR: Spatio-temporal Pooling One-Token Reconstruction for Universal Physiological Signal Self-supervised Learning](https://mlsanity.com/paper/2606.21973/) (2026)
- [Separating Expert Retention from Autonomous Source Inference in Raw-ECG-Replay-Free Continual ECG Deployment](https://mlsanity.com/paper/2607.01674/) (2026)
- [STAIL: Semantic Text-Anchored Incremental Learning for Medical Imaging via Large Language Models](https://mlsanity.com/paper/2608.05808/) (2026)

## Abstract (arXiv)

Continual Learning (CL) methods aim to learn from a sequence of tasks while avoiding the challenge of forgetting previous knowledge. We present DREAM-CL, a novel CL method for ECG arrhythmia detection that introduces dynamic prototype rehearsal memory. DREAM-CL selects representative prototypes by clustering data based on learning behavior during each training session. Within each cluster, we apply a smooth sorting operation that ranks samples by training difficulty, compressing extreme values and removing outliers. The more challenging samples are then chosen as prototypes for the rehearsal memory, ensuring effective knowledge retention across sessions. We evaluate our method on time-incremental, class-incremental, and lead-incremental scenarios using two widely used ECG arrhythmia datasets, Chapman and PTB-XL. The results demonstrate that DREAM-CL outperforms the state-of-the-art in CL for ECG arrhythmia detection. Detailed ablation and sensitivity studies are performed to validate the different design choices of our method.