# Gradient Episodic Memory with a Soft Constraint for Continual Learning

arXiv: https://arxiv.org/abs/2011.07801 · HTML: https://mlsanity.com/paper/2011.07801/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2020.

## Built on by (most cited first, 12 of 12)

- [Continual Learning for Monolingual End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2112.09427/) (2021)
- [Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method](https://mlsanity.com/paper/2406.16231/) (2024)
- [SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators](https://mlsanity.com/paper/2603.20410/) (2026)
- [Elastic Multi-Gradient Descent for Parallel Continual Learning](https://mlsanity.com/paper/2401.01054/) (2024)
- [Overcoming Domain Drift in Online Continual Learning](https://mlsanity.com/paper/2405.09133/) (2024)
- [Task-agnostic Lifelong Robot Learning with Retrieval-based Weighted Local Adaptation](https://mlsanity.com/paper/2410.02995/) (2024)
- [Continual Learning With Quasi-Newton Methods](https://mlsanity.com/paper/2503.19939/) (2025)
- [Outlook Towards Deployable Continual Learning for Particle Accelerators](https://mlsanity.com/paper/2504.03793/) (2025)
- [GEM-Style Constraints for PEFT with Dual Gradient Projection in LoRA](https://mlsanity.com/paper/2601.02500/) (2026)
- [Natural Gradient Descent for Online Continual Learning](https://mlsanity.com/paper/2603.20898/) (2026)
- [Reducing Per-Sample Interference in Stochastic Optimization](https://mlsanity.com/paper/2607.16261/) (2026)
- [Unsupervised Continual Learning with Growing Self-Organizing Maps and Synthetic Replay](https://mlsanity.com/paper/2608.27662/) (2026)

## Abstract (arXiv)

Catastrophic forgetting in continual learning is a common destructive phenomenon in gradient-based neural networks that learn sequential tasks, and it is much different from forgetting in humans, who can learn and accumulate knowledge throughout their whole lives. Catastrophic forgetting is the fatal shortcoming of a large decrease in performance on previous tasks when the model is learning a novel task. To alleviate this problem, the model should have the capacity to learn new knowledge and preserve learned knowledge. We propose an average gradient episodic memory (A-GEM) with a soft constraint ε ∈ [0, 1], which is a balance factor between learning new knowledge and preserving learned knowledge; our method is called gradient episodic memory with a soft constraint ε (ε-SOFT-GEM). ε-SOFT-GEM outperforms A-GEM and several continual learning benchmarks in a single training epoch; additionally, it has state-of-the-art average accuracy and efficiency for computation and memory, like A-GEM, and provides a better trade-off between the stability of preserving learned knowledge and the plasticity of learning new knowledge.