# CoMetaPNS: Continually Meta-learning Personalized Neural Surrogates for Cardiac Electrophysiology Simulations

arXiv: https://arxiv.org/abs/2606.07488 · HTML: https://mlsanity.com/paper/2606.07488/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 54 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels](https://mlsanity.com/paper/1711.08920/) (2017)
- [Task Agnostic Continual Learning via Meta Learning](https://mlsanity.com/paper/1906.05201/) (2019)
- [La-MAML: Look-ahead Meta Learning for Continual Learning](https://mlsanity.com/paper/2007.13904/) (2020)
- [Continuous Meta-Learning without Tasks](https://mlsanity.com/paper/1912.08866/) (2019)
- [Building high accuracy emulators for scientific simulations with deep neural architecture search](https://mlsanity.com/paper/2001.08055/) (2020)
- [Generative Modeling and Inverse Imaging of Cardiac Transmembrane Potential](https://mlsanity.com/paper/1905.04803/) (2019)
- [Bayesian Optimization on Large Graphs via a Graph Convolutional Generative Model: Application in Cardiac Model Personalization](https://mlsanity.com/paper/1907.01406/) (2019)
- [Few-shot Generation of Personalized Neural Surrogates for Cardiac Simulation via Bayesian Meta-Learning](https://mlsanity.com/paper/2210.02967/) (2022)
- [Learning Geometry-Dependent and Physics-Based Inverse Image Reconstruction](https://mlsanity.com/paper/2007.09522/) (2020)
- [A machine learning approach to reconstruction of heart surface potentials from body surface potentials](https://mlsanity.com/paper/1802.02240/) (2018)
- [Rethinking multiscale cardiac electrophysiology with machine learning and predictive modelling](https://mlsanity.com/paper/1810.04227/) (2018)
- [High-dimensional Bayesian Optimization of Personalized Cardiac Model Parameters via an Embedded Generative Model](https://mlsanity.com/paper/2005.07804/) (2020)
- [Full-field surrogate modeling of cardiac function encoding geometric variability](https://mlsanity.com/paper/2504.20479/) (2025)
- [Improving Generalization of Deep Networks for Inverse Reconstruction of Image Sequences](https://mlsanity.com/paper/1903.02948/) (2019)
- [Simulation of parametrized cardiac electrophysiology in three dimensions using physics-informed neural networks](https://mlsanity.com/paper/2506.15405/) (2025)

## Abstract (arXiv)

Personalized virtual heart simulations face challenges in model personalization and computational cost. While neural surrogates offer state-of-the-art solutions, they typically address either efficient personalization or training generalizable models. Recent work reframes this by learning the process of personalizing a surrogate using limited subject-specific context data, through few-shot generative modeling with set-conditioned surrogates and meta-learned amortized inference. These methods, however, assume a static and diverse training distribution with known task identifiers. When new data becomes available, they require costly retraining with all prior data to avoid catastrophic forgetting - a phenomena where the model forgets earlier tasks when trained on new ones. This is a major limitation in clinical settings where often unlabeled data arrives sequentially and full retraining is infeasible. This paper presents a new continual meta-learning framework to achieve personalized neural surrogates able to not only continually integrate information but also identify whether incoming data stems from a known or unknown dynamics source. By leveraging a continual Bayesian Gaussian Mixture Model over a memory buffer, our framework can infer the identifiers and relationships of data over time - required for effective meta-learning. Empirical results on synthetic cardiac data demonstrate superior simulation forecasting, computational scalability, and resilience to catastrophic forgetting compared to existing baselines.